© 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. 1-RES-JB
    11. 21045
    Prev
    Next
    INDEX
    Explanations

    mentions of 'human' in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Transcript
    -0.86
    INO
    -0.76
    forth
    -0.75
     Perry
    -0.75
    abb
    -0.73
    REP
    -0.72
     Compton
    -0.71
     Christensen
    -0.70
     Brewer
    -0.67
     Decker
    -0.67
    POSITIVE LOGITS
     beings
    1.25
     readable
    0.93
     rights
    0.93
    istic
    0.93
     human
    0.92
    itar
    0.91
     embryonic
    0.88
    rights
    0.86
    itarian
    0.84
    istically
    0.83
    Activations Density 0.022%

    No Known Activations