© 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. 2-RES-JB
    11. 9457
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    incidents and discussions around violent crime and its consequences

    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
    isSpecialOrderable
    -0.66
     incent
    -0.56
    soDeliveryDate
    -0.56
    ularity
    -0.55
    ahime
    -0.53
    EEK
    -0.52
    âĶĢâĶĢâĶĢâĶĢ
    -0.51
    Craft
    -0.50
    çīĪ
    -0.50
    itect
    -0.50
    POSITIVE LOGITS
     barric
    0.65
     unlawfully
    0.65
     roadside
    0.64
     police
    0.61
     illegally
    0.61
     undercover
    0.61
     abusive
    0.60
     tresp
    0.59
     NYPD
    0.59
    nsic
    0.59
    Activations Density 4.767%

    No Known Activations