© 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
    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. 20322
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and control

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors related to conformance or adherence

    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
     examiner
    -0.67
     designation
    -0.56
     Isles
    -0.54
     Franks
    -0.53
     deed
    -0.53
     supervisor
    -0.52
     dates
    -0.51
     tracker
    -0.51
     advisor
    -0.51
     recorder
    -0.51
    POSITIVE LOGITS
    oused
    0.87
    inged
    0.80
    ined
    0.80
    alled
    0.80
    icating
    0.79
    ited
    0.79
    iably
    0.78
    ibly
    0.77
    amb
    0.76
    ped
    0.76
    Activations Density 0.430%

    No Known Activations