© 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. 3-RES-JB
    11. 10715
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Levinson" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Lev" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.87
    REDACTED
    -0.76
    luaj
    -0.74
     Blessed
    -0.70
    lli
    -0.65
    ndum
    -0.64
    reference
    -0.64
     Incarnation
    -0.63
    ORGE
    -0.62
    ãģ§
    -0.61
    POSITIVE LOGITS
    itic
    1.48
    itating
    1.20
    isions
    1.18
    itated
    1.10
    itate
    1.09
    inson
    1.07
    antine
    1.05
    itation
    1.03
     Lev
    1.01
    itt
    1.00
    Activations Density 0.007%

    No Known Activations