© 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. 16802
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "lump."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "lump."

    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
    thel
    -0.71
    =-=-=-=-=-=-=-=-
    -0.66
    oir
    -0.66
     Esp
    -0.64
    acher
    -0.63
    HOME
    -0.62
     Fantasy
    -0.59
     Rafael
    -0.57
     Eug
    -0.56
     Prev
    -0.56
    POSITIVE LOGITS
     lump
    1.51
     Lump
    0.94
    ãĤ©
    0.92
    wagon
    0.83
    untarily
    0.82
    isode
    0.80
    umin
    0.80
    ular
    0.77
     pigeon
    0.76
    enary
    0.76
    Activations Density 0.009%

    No Known Activations