© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 6077
    Prev
    Next
    INDEX
    Explanations

    the word "Bend" occurring in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations, particularly "Bend"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spoken
    -0.72
     persuasive
    -0.69
     premium
    -0.65
     adv
    -0.63
     readable
    -0.63
     achie
    -0.61
     SERVICE
    -0.60
     conclud
    -0.60
     deduction
    -0.60
    */(
    -0.60
    POSITIVE LOGITS
     Bend
    1.36
    SourceFile
    0.91
    stead
    0.90
    boro
    0.88
    pole
    0.88
     Rib
    0.84
    itude
    0.83
    oms
    0.82
    olini
    0.81
    eret
    0.79
    Activations Density 0.008%

    No Known Activations