© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20884
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Imm" related to immigrants or immigration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to the word "Immortal"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ļéĨĴ
    -0.94
    */(
    -0.93
    uyomi
    -0.87
     Chevron
    -0.73
     Byrd
    -0.71
     CPC
    -0.69
    å§«
    -0.69
     Randolph
    -0.69
    rists
    -0.67
     deeds
    -0.66
    POSITIVE LOGITS
    igrant
    1.27
    igrants
    1.21
     Imm
    1.12
    igr
    1.08
    Imm
    1.06
    igration
    1.02
    idious
    0.99
    imm
    0.98
    ortality
    0.97
    igrated
    0.93
    Activations Density 0.005%

    No Known Activations