© 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. 8-RES-JB
    11. 9060
    Prev
    Next
    INDEX
    Explanations

    words related to communication, dialogue, and consultation

    oai_token-act-pair · gpt-3.5-turbo

    instances of consultations or discussions between parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĺ
    -0.74
    apo
    -0.68
    utterstock
    -0.66
    escape
    -0.63
    iru
    -0.63
     Dancing
    -0.63
     Falling
    -0.63
     gore
    -0.62
     Miracle
    -0.61
    }}
    -0.61
    POSITIVE LOGITS
     consultations
    1.08
     consultation
    1.03
     briefed
    1.03
     consulted
    1.00
     discussions
    0.99
     internally
    0.98
     advisors
    0.97
     feasibility
    0.95
     brainstorm
    0.95
     enqu
    0.89
    Activations Density 0.574%

    No Known Activations