© 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. 19517
    Prev
    Next
    INDEX
    Explanations

    references to legal matters

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms related to people

    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
    etheless
    -0.67
    Ļ½
    -0.67
    ãĥ¼ãĥ«
    -0.62
    jection
    -0.62
     Few
    -0.60
    İĭ
    -0.59
     Archangel
    -0.59
    ject
    -0.59
     eclipse
    -0.59
     cour
    -0.58
    POSITIVE LOGITS
    ',
    0.80
    ELF
    0.78
    Cause
    0.75
    cause
    0.73
    Mech
    0.72
    Hom
    0.71
    Interstitial
    0.69
     own
    0.68
    Own
    0.65
    Brien
    0.64
    Activations Density 0.048%

    No Known Activations