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

    Neuronpedia

    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. 23844
    Prev
    Next
    INDEX
    Explanations

    phrases related to beliefs and judgments

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to perception and societal beliefs

    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
    Attempts
    -0.68
    fax
    -0.63
    sever
    -0.63
    ioch
    -0.62
    swick
    -0.62
    legram
    -0.62
    Details
    -0.61
     sidx
    -0.60
    Multiple
    -0.60
    .<
    -0.60
    POSITIVE LOGITS
     somehow
    1.02
     infall
    0.96
     superiority
    0.84
     invincible
    0.84
     inherently
    0.84
     magically
    0.82
     invented
    0.73
     inferior
    0.72
     paradise
    0.72
     immoral
    0.70
    Activations Density 0.656%

    No Known Activations