© 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. 6-RES-JB
    6. 731
    Prev
    Next
    INDEX
    Explanations

    commands or directives given by an authority figure or person in power

    oai_token-act-pair · gpt-3.5-turbo

    instances of commands or directives given by authoritative figures

    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
    ãĤ©
    -0.79
    pmwiki
    -0.70
    ãĤ§
    -0.69
    tex
    -0.69
    Tang
    -0.68
    attery
    -0.68
    burgh
    -0.66
    cit
    -0.66
     Wink
    -0.65
     Sack
    -0.65
    POSITIVE LOGITS
    lies
    0.80
    etary
    0.80
     confir
    0.75
    uria
    0.71
     cancell
    0.68
     ordering
    0.68
    ordering
    0.66
     involuntary
    0.65
     groceries
    0.65
    ograph
    0.65
    Activations Density 0.026%

    No Known Activations