© 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. 4-RES-JB
    11. 414
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or going back

    oai_token-act-pair · gpt-3.5-turbo

    references to navigation or orientation in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inational
    -0.68
    ×IJ
    -0.66
    izo
    -0.65
     viz
    -0.62
    cigarette
    -0.59
    ihad
    -0.59
    7601
    -0.59
    nt
    -0.59
    itsu
    -0.59
     constitu
    -0.58
    POSITIVE LOGITS
    wards
    1.07
    GROUND
    1.04
    dated
    1.02
    lash
    1.00
    door
    0.96
    packs
    0.95
    )=(
    0.92
    ward
    0.92
    gam
    0.90
    tracking
    0.90
    Activations Density 0.027%

    No Known Activations