Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14569
    Prev
    Next
    INDEX
    Explanations

    verbs indicating potential outcomes or effects

    oai_token-act-pair · gpt-3.5-turbo

    critical situations or events that could lead to significant consequences

    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
     requests
    -0.68
     appropriated
    -0.68
     tuned
    -0.66
     coefficients
    -0.66
    */(
    -0.65
     allocated
    -0.64
     observation
    -0.64
     impulses
    -0.64
     inputs
    -0.64
     faculties
    -0.63
    POSITIVE LOGITS
     doom
    1.14
     Armageddon
    0.97
     downfall
    0.93
     disastrous
    0.90
     havoc
    0.90
     engulf
    0.88
     bloodshed
    0.83
     ruin
    0.83
     fate
    0.81
     mayhem
    0.81
    Activations Density 0.460%

    No Known Activations