© 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. 19811
    Prev
    Next
    INDEX
    Explanations

    references to the current state or condition

    oai_token-act-pair · gpt-3.5-turbo

    references to the state or status of a situation

    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
    aliation
    -0.81
    amy
    -0.81
    uddin
    -0.81
    wright
    -0.76
    romeda
    -0.74
    agree
    -0.73
    essen
    -0.72
    hod
    -0.71
    aths
    -0.71
    acked
    -0.71
    POSITIVE LOGITS
     incarnation
    1.22
     iteration
    1.05
     predicament
    1.04
     spate
    0.93
     situation
    0.90
     generation
    0.90
     crop
    0.87
     whereabouts
    0.86
     occupant
    0.86
     edition
    0.86
    Activations Density 0.026%

    No Known Activations