© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 23954
    Prev
    Next
    INDEX
    Explanations

    mentions of public statements or declarations related to governmental matters, particularly security breaches

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to public sentiment or community reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.66
     magician
    -0.64
    Jr
    -0.59
    ãĥīãĥ©ãĤ´ãĥ³
    -0.59
     solves
    -0.59
    sama
    -0.58
    è¦ļéĨĴ
    -0.57
    ogun
    -0.56
     XD
    -0.56
    gom
    -0.56
    POSITIVE LOGITS
     themselves
    1.23
    selves
    1.18
     collectively
    0.89
     selves
    0.89
     husbands
    0.82
    aughtered
    0.78
     boycott
    0.74
     ballots
    0.74
     their
    0.73
    their
    0.73
    Activations Density 0.991%

    No Known Activations