© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12128
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical attributes or conditions, particularly those related to being exposed or minimalistic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bare" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°Ĩ
    -0.82
    abulary
    -0.76
     Publishers
    -0.74
    ormon
    -0.72
    MRI
    -0.72
    alez
    -0.71
    oldemort
    -0.71
    anwhile
    -0.71
    agents
    -0.68
    oldown
    -0.68
    POSITIVE LOGITS
    footed
    1.08
    faced
    1.02
     bare
    1.01
    foot
    0.96
    bones
    0.93
    chest
    0.89
    clad
    0.88
    feet
    0.87
    handed
    0.83
    bly
    0.81
    Activations Density 0.008%

    No Known Activations