© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15407
    Prev
    Next
    INDEX
    Explanations

    locations or proper nouns representing places

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and references to specific places

    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
    brids
    -0.47
    paio
    -0.47
    isites
    -0.45
    letes
    -0.45
    umbnails
    -0.43
    rogens
    -0.43
    ographers
    -0.42
    rehensive
    -0.41
    apego
    -0.40
    POR
    -0.40
    POSITIVE LOGITS
     guise
    0.67
     fashion
    0.53
     vicinity
    0.52
    é¾įå¥ij士
    0.49
     Bay
    0.48
     Indies
    0.48
     circles
    0.47
     harbour
    0.45
     manner
    0.45
     derby
    0.44
    Activations Density 1.613%

    No Known Activations