Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 20734
    Prev
    Next
    INDEX
    Explanations

    phrases related to various impacts on physical conditions or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to causes and effects of health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afety
    -0.67
     Goes
    -0.65
    KR
    -0.61
     unfocusedRange
    -0.60
     Malk
    -0.60
    hess
    -0.59
    OIL
    -0.58
     (@
    -0.58
     Kom
    -0.57
     Stupid
    -0.56
    POSITIVE LOGITS
     respectively
    1.61
     alike
    1.11
     attest
    0.89
     collectively
    0.87
     converge
    0.85
     commonplace
    0.81
     combined
    0.78
     respective
    0.77
     abound
    0.77
     together
    0.74
    Activations Density 0.652%

    No Known Activations