© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1850
    Prev
    Next
    INDEX
    Explanations

    names of people or characters, potentially with a focus on surnames

    oai_token-act-pair · gpt-3.5-turbo

    specific names and terms related to individuals or entities, particularly focusing on surnames and certain notable references

    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
    ilial
    -0.92
    boards
    -0.68
    ously
    -0.68
    çķ
    -0.66
     reception
    -0.65
    ZI
    -0.64
    士
    -0.64
    board
    -0.64
    apter
    -0.63
    ptin
    -0.63
    POSITIVE LOGITS
     Vik
    0.97
    ĸļ
    0.87
    apore
    0.87
    icious
    0.84
     Varg
    0.79
    anova
    0.78
     Alonso
    0.78
    eks
    0.74
    ileaks
    0.73
    oslav
    0.72
    Activations Density 0.020%

    No Known Activations