© 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. 2-RES-JB
    11. 9260
    Prev
    Next
    INDEX
    Explanations

    references to paths or courses of action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "track" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    doms
    -0.72
    aples
    -0.64
    Ann
    -0.64
    endiary
    -0.61
     advent
    -0.61
    acco
    -0.60
    ortium
    -0.60
     pand
    -0.60
    ince
    -0.60
     International
    -0.58
    POSITIVE LOGITS
    tracks
    1.08
     Tracks
    1.07
    track
    1.05
     tracks
    1.04
     track
    1.00
    masters
    0.91
    Track
    0.85
    course
    0.83
     Track
    0.82
    suit
    0.82
    Activations Density 0.013%

    No Known Activations