© 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. 9-RES-JB
    11. 1591
    Prev
    Next
    INDEX
    Explanations

    words related to crime and criminal actions

    oai_token-act-pair · gpt-3.5-turbo

    information related to criminal activity and law enforcement reports

    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
     Perspect
    -0.64
     Travels
    -0.62
    yssey
    -0.61
    ggles
    -0.60
    sometimes
    -0.60
    ortment
    -0.59
    HCR
    -0.59
    yon
    -0.59
    arity
    -0.59
    eals
    -0.59
    POSITIVE LOGITS
     whatsoever
    1.50
     nor
    1.21
    soever
    1.00
     anywhere
    0.96
     anymore
    0.89
     except
    0.89
    nor
    0.87
    except
    0.84
     harmed
    0.83
     detectable
    0.80
    Activations Density 0.288%

    No Known Activations