© 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. 4-RES-JB
    11. 6733
    Prev
    Next
    INDEX
    Explanations

    phrases indicating file extensions, such as ".exe" or ".pdf"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "Ext" or "ext" in various contexts

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

    No Comments

    Negative Logits
    hari
    -0.98
    Downloadha
    -0.83
    folk
    -0.83
    ker
    -0.82
    maid
    -0.82
    Reviewer
    -0.76
    zza
    -0.74
    hart
    -0.72
    ghai
    -0.71
     Bard
    -0.70
    POSITIVE LOGITS
    ensions
    1.42
    racted
    1.41
    ension
    1.37
    inct
    1.35
    ract
    1.30
    raction
    1.26
    ortion
    1.16
    ractor
    1.15
    ended
    1.13
    inction
    1.10
    Activations Density 0.006%

    No Known Activations