© 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. 8-RES-JB
    11. 6115
    Prev
    Next
    INDEX
    Explanations

    terms related to water and its properties

    oai_token-act-pair · gpt-3.5-turbo

    references to water and its properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •a quick list

    No Comments

    Negative Logits
    eering
    -0.88
    Reloaded
    -0.76
    ures
    -0.71
    Files
    -0.68
    ificant
    -0.67
     Amend
    -0.66
    ature
    -0.65
    -+-+
    -0.64
    uate
    -0.64
    ablishment
    -0.64
    POSITIVE LOGITS
    melon
    1.75
    tight
    1.22
    colour
    1.15
    falls
    1.14
    mel
    1.02
    color
    0.96
    loo
    0.96
    proof
    0.95
     soluble
    0.95
     fluor
    0.93
    Activations Density 0.061%

    No Known Activations