© 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. 8841
    Prev
    Next
    INDEX
    Explanations

    keywords related to numbers

    oai_token-act-pair · gpt-3.5-turbo

    temporal references related to specific decades

    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
    tnc
    -0.65
    Ĥª
    -0.62
     Krishna
    -0.61
    ¬¼
    -0.61
    ĺħ
    -0.59
     pine
    -0.59
     explicit
    -0.59
     rom
    -0.58
    ħĭ
    -0.58
     rig
    -0.58
    POSITIVE LOGITS
    kit
    0.75
    majority
    0.74
    south
    0.69
    agna
    0.68
    jab
    0.67
    trak
    0.65
    usalem
    0.64
     surv
    0.63
    generation
    0.63
    gencies
    0.63
    Activations Density 0.000%

    No Known Activations