© 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. 9036
    Prev
    Next
    INDEX
    Explanations

    terms related to providing support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    the word "supp" and its variations, indicating a focus on support or suggesting something

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.69
     Warsaw
    -0.65
     Blazers
    -0.65
     malice
    -0.64
     betrayal
    -0.63
    pan
    -0.62
     Nanto
    -0.62
    fish
    -0.61
     Bravo
    -0.61
     logger
    -0.60
    POSITIVE LOGITS
    ression
    1.33
    orter
    1.28
    lication
    1.28
    orters
    1.28
    ressor
    1.24
    lied
    1.24
    ressive
    1.23
    ressed
    1.21
    ortun
    1.15
    ressing
    1.11
    Activations Density 0.018%

    No Known Activations