© 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. 10-RES-JB
    11. 14961
    Prev
    Next
    INDEX
    Explanations

    mentions of public entities, government-related opinions, and statistical information

    oai_token-act-pair · gpt-3.5-turbo

    references to social and political issues affecting the public

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cooldown
    -0.60
    ++;
    -0.59
     };
    -0.58
     typed
    -0.54
     tweeted
    -0.53
    cffff
    -0.52
     trough
    -0.51
     Accessed
    -0.51
     sclerosis
    -0.51
     streng
    -0.51
    POSITIVE LOGITS
     to
    0.94
    to
    0.80
    ucket
    0.64
    ¿
    0.63
     whether
    0.59
    nih
    0.57
    ²¾
    0.57
    ador
    0.57
    To
    0.55
     TO
    0.55
    Activations Density 0.384%

    No Known Activations