© 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. 19636
    Prev
    Next
    INDEX
    Explanations

    mentions of the durability or durability of objects or materials

    oai_token-act-pair · gpt-3.5-turbo

    terms related to durability and sturdiness

    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
    ffic
    -0.84
    athetic
    -0.83
    udic
    -0.80
    olitan
    -0.78
    ean
    -0.76
    chie
    -0.75
    olic
    -0.75
    atics
    -0.74
    apa
    -0.73
    onia
    -0.73
    POSITIVE LOGITS
     durability
    1.20
     durable
    1.18
     conclud
    0.83
     charact
    0.82
     mathemat
    0.81
     corrid
    0.80
     dur
    0.79
     glue
    0.78
     adhesive
    0.76
    adoes
    0.76
    Activations Density 0.014%

    No Known Activations