© 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. 18587
    Prev
    Next
    INDEX
    Explanations

    phrases related to narratives and portrayals of events or individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to portrayals and narratives relating to individuals or groups

    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
    iland
    -0.73
     awoken
    -0.71
     resid
    -0.69
    ktop
    -0.68
    HOU
    -0.65
     clocks
    -0.64
    cyl
    -0.63
     resides
    -0.62
     drafts
    -0.62
    sterdam
    -0.62
    POSITIVE LOGITS
     blame
    1.00
     disrespect
    0.91
     discredit
    0.90
     hypocrisy
    0.89
     scapego
    0.87
     culp
    0.87
    å§
    0.86
     unfairly
    0.83
    racist
    0.83
     innocence
    0.83
    Activations Density 0.630%

    No Known Activations