© 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. 10-RES-JB
    11. 10783
    Prev
    Next
    INDEX
    Explanations

    technical terms and file-related information

    oai_token-act-pair · gpt-3.5-turbo

    components related to technical file handling and error management in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.79
    soDeliveryDate
    -0.79
    utsche
    -0.75
    ths
    -0.74
    waves
    -0.73
    ende
    -0.69
    bush
    -0.68
     discreet
    -0.68
    ads
    -0.67
    wark
    -0.67
    POSITIVE LOGITS
     detected
    1.11
     configured
    1.08
     specified
    1.08
     loaded
    1.05
     mismatch
    1.04
     installed
    1.04
     invalid
    1.01
     expired
    0.99
    Invalid
    0.98
     exceeded
    0.96
    Activations Density 0.233%

    No Known Activations