Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7820
    Prev
    Next
    INDEX
    Explanations

    references to freedom of speech or related rights mentioned in documents

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of free speech and related rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tom
    -0.70
    BALL
    -0.68
     Stab
    -0.65
    à¤
    -0.65
    etta
    -0.65
    git
    -0.65
     CET
    -0.64
    ETS
    -0.64
    ARDS
    -0.64
    nec
    -0.64
    POSITIVE LOGITS
     rights
    1.10
     Rights
    0.98
     protections
    0.95
    rights
    0.91
     freedoms
    0.91
     liberties
    0.90
    speech
    0.88
     advocates
    0.88
     activism
    0.84
     pamph
    0.84
    Activations Density 0.051%

    No Known Activations