© 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. 18268
    Prev
    Next
    INDEX
    Explanations

    words ending in 'late' or containing the word 'late'

    oai_token-act-pair · gpt-3.5-turbo

    references to latitude 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
    OHN
    -1.06
    rahim
    -0.89
    Shell
    -0.83
    stasy
    -0.82
    PO
    -0.80
    perty
    -0.77
    displayText
    -0.76
    âĶģ
    -0.76
    PROV
    -0.75
    Discussion
    -0.74
    POSITIVE LOGITS
     lat
    1.12
    itudinal
    1.08
    itudes
    1.07
    itude
    1.04
    itud
    0.99
    imes
    0.97
    lat
    0.80
     lith
    0.74
     basin
    0.71
    iencies
    0.70
    Activations Density 0.007%

    No Known Activations