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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9064
    Prev
    Next
    INDEX
    Explanations

    references to legislative or legal discussions on same-sex marriage

    oai_token-act-pair · gpt-3.5-turbo

    references to same-sex marriage

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

    No Comments

    Negative Logits
    OST
    -0.70
    ostic
    -0.70
    arest
    -0.68
    erest
    -0.67
    liest
    -0.67
     Bulg
    -0.67
    akings
    -0.67
    efully
    -0.65
    ç«
    -0.64
    ASE
    -0.61
    POSITIVE LOGITS
    rity
    0.80
    gender
    0.77
     vein
    0.76
    nesota
    0.74
     exact
    0.73
    fam
    0.71
    sex
    0.70
     nationality
    0.68
    amphetamine
    0.68
    bilt
    0.67
    Activations Density 0.032%

    No Known Activations