© 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. 6-RES-JB
    11. 18019
    Prev
    Next
    INDEX
    Explanations

    technical information and instructions in a structured format

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to digital interactions and user experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.68
     prosecutions
    -0.67
    outhern
    -0.63
     whistleblowers
    -0.61
     whistleblower
    -0.60
     politic
    -0.59
    political
    -0.58
    nsic
    -0.55
     prosecut
    -0.54
     Journalism
    -0.54
    POSITIVE LOGITS
     XY
    0.69
    Quantity
    0.69
     or
    0.69
     etc
    0.68
    "))
    0.67
     predetermined
    0.67
    ?".
    0.66
    )).
    0.65
    omever
    0.64
    arsity
    0.63
    Activations Density 1.793%

    No Known Activations