© 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. 3507
    Prev
    Next
    INDEX
    Explanations

    verbs related to abandoning or disregarding something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ditch."

    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
    cas
    -0.72
    ctic
    -0.69
    ctica
    -0.69
    tesy
    -0.68
    Guard
    -0.66
    prot
    -0.66
    estones
    -0.66
    bi
    -0.65
    sterdam
    -0.63
    adr
    -0.63
    POSITIVE LOGITS
    itching
    1.15
    itched
    1.01
    itches
    0.89
     whine
    0.76
    fork
    0.73
    itcher
    0.72
    ernel
    0.71
    ibilities
    0.68
     Scroll
    0.67
    weed
    0.67
    Activations Density 0.011%

    No Known Activations