© 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. 3-RES-JB
    11. 10793
    Prev
    Next
    INDEX
    Explanations

    names, likely of people or characters, preceded by 'Gu'

    oai_token-act-pair · gpt-3.5-turbo

    names and terms associated with guerrilla-related themes or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resid
    -0.80
     adolesc
    -0.74
     Journals
    -0.69
     reversible
    -0.68
     adop
    -0.67
     RELEASE
    -0.65
     unfocusedRange
    -0.65
     fertility
    -0.64
     citiz
    -0.64
     stru
    -0.63
    POSITIVE LOGITS
    utan
    1.01
    anamo
    0.99
    ieri
    0.89
    ault
    0.84
    gio
    0.80
    fecture
    0.80
    anan
    0.79
    azard
    0.78
    olin
    0.77
    ppe
    0.77
    Activations Density 0.081%

    No Known Activations