© 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. 8088
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "overdose."

    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
     ann
    -0.66
     reciproc
    -0.61
     envy
    -0.59
     Lemon
    -0.58
     interchange
    -0.57
     GB
    -0.57
     dissu
    -0.54
     gel
    -0.54
     Gel
    -0.54
    dom
    -0.53
    POSITIVE LOGITS
    osed
    4.44
    osing
    2.43
    oses
    2.30
    OSED
    2.26
    ose
    1.85
    OSE
    1.72
    oser
    1.54
    osis
    1.31
    osal
    1.31
    onent
    1.24
    Activations Density 0.007%

    No Known Activations