© 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. 3128
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an attempt to achieve something without success

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "avail" and its variations

    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
    eric
    -0.84
     Nose
    -0.70
    iber
    -0.66
    irrel
    -0.65
     Crus
    -0.65
     Grove
    -0.63
    mac
    -0.63
    odor
    -0.62
     Prison
    -0.61
    hon
    -0.61
    POSITIVE LOGITS
     avail
    1.46
     mathemat
    1.08
    ĸļ
    1.04
    abilities
    0.96
    urations
    0.87
     vulner
    0.82
    ilities
    0.81
    edIn
    0.81
     agre
    0.81
    ilege
    0.80
    Activations Density 0.006%

    No Known Activations