© 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. 8446
    Prev
    Next
    INDEX
    Explanations

    mentions of being physically stuck or restricted.

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "trapped"

    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
    edly
    -0.82
    eds
    -0.76
    sych
    -0.72
    issance
    -0.68
    esan
    -0.68
     praises
    -0.60
    office
    -0.59
    minus
    -0.59
     Carbuncle
    -0.59
    ss
    -0.59
    POSITIVE LOGITS
     trapped
    1.00
    ĸļ
    0.83
     trapping
    0.82
    ©¶æ¥µ
    0.81
    ÃįÃį
    0.80
    ngth
    0.79
    ÃĥÃĤ
    0.74
    ModLoader
    0.73
    door
    0.72
    ãĥĺ
    0.71
    Activations Density 0.010%

    No Known Activations