© 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. 2-RES-JB
    6. 4061
    Prev
    Next
    INDEX
    Explanations

    words related to coordinates or ordinal numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "cord" in various contexts

    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
    )=(
    -0.68
    CVE
    -0.68
     midterm
    -0.65
    prus
    -0.63
     goodness
    -0.63
     scent
    -0.62
    =-=-=-=-
    -0.61
    cled
    -0.61
     palms
    -0.60
     spectrum
    -0.60
    POSITIVE LOGITS
    inator
    1.08
    inates
    1.06
    nance
    1.05
    inated
    1.02
    ination
    1.01
    inarily
    0.96
    inances
    0.92
    inating
    0.91
    ont
    0.89
    inators
    0.88
    Activations Density 0.011%

    No Known Activations