© 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. 11-RES-JB
    11. 6952
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames or handles

    oai_token-act-pair · gpt-3.5-turbo

    patterns or elements related to social media URLs or handles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     condensed
    -0.76
     afore
    -0.72
     bombard
    -0.70
     reconstruct
    -0.68
     corrections
    -0.65
     caring
    -0.65
    ortunately
    -0.65
     strategist
    -0.64
     suspense
    -0.63
     stuffing
    -0.63
    POSITIVE LOGITS
    Gh
    1.38
    Pg
    1.35
    GY
    1.34
    OY
    1.33
    RN
    1.33
    Ay
    1.32
    ZX
    1.32
    Eh
    1.32
    ZI
    1.32
    Cu
    1.32
    Activations Density 0.055%

    No Known Activations