© 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. 4470
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'usage'

    oai_token-act-pair · gpt-3.5-turbo

    references to data usage and its implications

    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
    tell
    -0.75
    inosaur
    -0.74
    abella
    -0.67
    hair
    -0.65
    bitious
    -0.64
    hedral
    -0.63
    arine
    -0.62
     Barg
    -0.60
    orb
    -0.60
    rop
    -0.59
    POSITIVE LOGITS
     habits
    0.98
    ername
    0.87
    iences
    0.82
     patterns
    0.72
    ickr
    0.71
    TOP
    0.70
    notations
    0.69
     interfaces
    0.68
    fulness
    0.67
    icides
    0.67
    Activations Density 0.031%

    No Known Activations