© 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. 0-RES-JB
    11. 1140
    Prev
    Next
    INDEX
    Explanations

    mentions of the element "iron" at various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to iron

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Privacy
    -0.81
    paces
    -0.76
    ñ
    -0.73
    ungle
    -0.68
     Chapman
    -0.68
     Scion
    -0.68
    Spons
    -0.67
    sterdam
    -0.66
    parents
    -0.66
     Splash
    -0.66
    POSITIVE LOGITS
     iron
    3.86
    Iron
    2.28
     Iron
    2.21
    iron
    2.11
     steel
    1.50
     copper
    1.46
     zinc
    1.46
     aluminium
    1.29
     metal
    1.24
     granite
    1.22
    Activations Density 0.013%

    No Known Activations