© 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. 8-RES-JB
    11. 18497
    Prev
    Next
    INDEX
    Explanations

    keywords related to hosting or hosts

    oai_token-act-pair · gpt-3.5-turbo

    references to a "host" or hosting entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rite
    -0.82
    utherford
    -0.67
    illard
    -0.63
    YP
    -0.62
    20439
    -0.62
    âĨij
    -0.61
    zb
    -0.60
     Dup
    -0.60
     MacArthur
    -0.59
     bilateral
    -0.58
    POSITIVE LOGITS
    esses
    1.25
    ess
    1.11
    name
    1.03
    ilities
    0.99
    names
    0.97
    ility
    0.92
    emark
    0.91
    el
    0.79
    ivity
    0.78
    ile
    0.78
    Activations Density 0.040%

    No Known Activations