© 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. 17004
    Prev
    Next
    INDEX
    Explanations

    phrases related to paving the way for future events or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to creating pathways or opportunities for future developments

    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
    agara
    -0.67
    bite
    -0.63
     Dahl
    -0.62
     Somers
    -0.61
    central
    -0.61
    inately
    -0.60
     pneum
    -0.59
    idious
    -0.59
    lua
    -0.58
     Grimm
    -0.58
    POSITIVE LOGITS
     pave
    1.05
     paving
    0.98
    roleum
    0.96
     paved
    0.84
     groundwork
    0.83
    \\\\\\\\
    0.82
    lete
    0.82
     pavement
    0.81
    \\\\
    0.80
    hurst
    0.79
    Activations Density 0.029%

    No Known Activations