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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-RES-JB
    6. 5633
    Prev
    Next
    INDEX
    Explanations

    words related to acts of bravery or assertiveness

    oai_token-act-pair · gpt-3.5-turbo

    words indicating actions and characteristics related to behavior and decision-making

    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
    anon
    -0.76
     ILCS
    -0.73
     MacBook
    -0.69
     bruises
    -0.69
    Stars
    -0.64
    olor
    -0.63
     downed
    -0.62
     Medals
    -0.62
    pedia
    -0.62
    illions
    -0.62
    POSITIVE LOGITS
     deliberate
    0.84
     aimed
    0.79
     proactive
    0.78
    Aim
    0.78
     toward
    0.74
     towards
    0.74
     promoting
    0.73
     deliberately
    0.73
     adherence
    0.73
     purposefully
    0.72
    Activations Density 0.561%

    No Known Activations