© 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. 24090
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "took place"

    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
    gp
    -0.70
    rc
    -0.69
    ONSORED
    -0.68
    iscal
    -0.67
    asted
    -0.66
    pired
    -0.65
    idth
    -0.65
     Griffith
    -0.63
    ight
    -0.63
    ights
    -0.62
    POSITIVE LOGITS
    down
    0.76
    holder
    0.75
    upon
    0.74
    ãĤª
    0.74
    bos
    0.73
    Place
    0.73
     Places
    0.71
    places
    0.71
    Magikarp
    0.70
    Ú
    0.70
    Activations Density 0.027%

    No Known Activations