© 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. 24212
    Prev
    Next
    INDEX
    Explanations

    phrases related to Tasmanian locations or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to Tasmania and related geographical terms

    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
    akening
    -0.74
    vel
    -0.72
    gio
    -0.72
    ©¶æ
    -0.71
    veland
    -0.70
     tremend
    -0.68
    ramid
    -0.68
    vy
    -0.68
    olas
    -0.67
    andr
    -0.65
    POSITIVE LOGITS
     Tasman
    1.22
     Hots
    0.95
     Tasmania
    0.87
    manship
    0.79
    gob
    0.77
     "$:/
    0.74
     Guinea
    0.73
    iana
    0.73
    Sax
    0.72
     Sturgeon
    0.72
    Activations Density 0.017%

    No Known Activations