© 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. 24175
    Prev
    Next
    INDEX
    Explanations

    references to specific technical terms and methods related to computer programming, such as code structure and functions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific character sequences or terms related to biochemical processes

    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
     Flight
    -0.67
     Shooter
    -0.67
     Nex
    -0.66
     Bench
    -0.65
     DSL
    -0.64
     Fang
    -0.64
     Myst
    -0.64
     purse
    -0.64
     torque
    -0.63
     Ic
    -0.63
    POSITIVE LOGITS
    acters
    1.82
    char
    1.08
    ribly
    0.90
    iana
    0.88
    ucky
    0.86
    sburgh
    0.86
    rament
    0.85
    acter
    0.83
    ofer
    0.82
    olesterol
    0.80
    Activations Density 0.023%

    No Known Activations