© 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. 9-RES-JB
    11. 4868
    Prev
    Next
    INDEX
    Explanations

    common verbs indicating perception or observation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to observation and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovie
    -0.81
    raft
    -0.79
    wake
    -0.73
    nor
    -0.71
    protect
    -0.70
    ocide
    -0.68
    umar
    -0.66
    sett
    -0.66
    aim
    -0.66
    lat
    -0.65
    POSITIVE LOGITS
     yourself
    1.16
     yourselves
    1.14
     plenty
    0.98
     lots
    0.93
     references
    0.91
     fewer
    0.89
     tons
    0.81
     something
    0.80
     your
    0.79
     occasional
    0.78
    Activations Density 0.161%

    No Known Activations