© 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. 1-RES-JB
    11. 20739
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to standards or common practices

    oai_token-act-pair · gpt-3.5-turbo

    references to societal or cultural standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.74
    cigarette
    -0.70
    lder
    -0.70
    âĵĺ
    -0.68
    pta
    -0.65
    cigarettes
    -0.65
    aska
    -0.64
    Topics
    -0.63
     Cann
    -0.61
     Bot
    -0.61
    POSITIVE LOGITS
     norm
    1.16
    norm
    1.10
    ality
    1.06
    ativity
    0.95
    eus
    0.82
    als
    0.81
    ãĥ¼ãĥĨ
    0.80
    mble
    0.79
    inarily
    0.79
    byss
    0.78
    Activations Density 0.007%

    No Known Activations