© 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. 1-RES-JB
    11. 16336
    Prev
    Next
    INDEX
    Explanations

    the name "Elli" in varying contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names and entities, particularly in a narrative or descriptive context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Malays
    -0.62
    nel
    -0.62
    NOR
    -0.62
     Kingdoms
    -0.61
     adoptive
    -0.60
    unks
    -0.58
     newsp
    -0.58
     Gum
    -0.57
    mal
    -0.57
    Reply
    -0.56
    POSITIVE LOGITS
    elli
    1.23
    opsis
    1.10
    quist
    0.94
    ucci
    0.93
    otti
    0.87
    ardi
    0.85
    issance
    0.83
    oche
    0.83
    otto
    0.81
    jection
    0.81
    Activations Density 0.007%

    No Known Activations