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. 10-RES-JB
    6. 6784
    Prev
    Next
    INDEX
    Explanations

    phrases related to estimates or evaluations of cost, value, or quantity

    oai_token-act-pair · gpt-3.5-turbo

    financial estimates and projections

    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
    odox
    -0.71
    soType
    -0.68
     POV
    -0.65
     inconsistency
    -0.61
     jealousy
    -0.61
     handcuffs
    -0.60
    fml
    -0.60
     innocence
    -0.60
     precon
    -0.59
     banter
    -0.59
    POSITIVE LOGITS
     totaled
    1.16
     averaged
    1.11
     total
    1.11
     estimated
    1.10
     amounted
    1.09
     racked
    1.06
    Total
    1.05
     gross
    1.04
     totaling
    1.02
     amassed
    1.01
    Activations Density 0.591%

    No Known Activations