© 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. 10-RES-JB
    6. 12699
    Prev
    Next
    INDEX
    Explanations

    prefixes or affixes that usually signify a specific meaning, such as 'de-' indicating reversal or removal

    oai_token-act-pair · gpt-3.5-turbo

    specific references to quantities and measures in various contexts

    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
     favourable
    -0.73
    Firstly
    -0.72
     analyse
    -0.71
     Whilst
    -0.71
     organise
    -0.69
     learnt
    -0.68
     practise
    -0.66
     whilst
    -0.66
     analys
    -0.65
     colours
    -0.65
    POSITIVE LOGITS
     DEA
    0.57
     Huckabee
    0.55
     Philly
    0.54
     Tennessee
    0.52
     NAACP
    0.52
     DeVos
    0.51
     LAPD
    0.51
    —"
    0.51
     Arpaio
    0.50
     attorney
    0.50
    Activations Density 1.943%

    No Known Activations