© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 6609
    Prev
    Next
    INDEX
    Explanations

    academic titles and degrees mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to academic degrees

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

    No Comments

    Negative Logits
    ppo
    -0.76
    ãĤ¼
    -0.71
     Crom
    -0.68
     Fo
    -0.67
    éĹĺ
    -0.67
     Wem
    -0.66
     convenience
    -0.66
     TMZ
    -0.66
    ãĥ¼ãĥ³
    -0.64
    RPG
    -0.64
    POSITIVE LOGITS
    ollar
    0.84
    ultz
    0.82
     dissertation
    0.78
    aughter
    0.78
    illing
    0.77
    heses
    0.75
     Examination
    0.75
    ollen
    0.74
     MPH
    0.74
    ennis
    0.74
    Activations Density 0.014%

    No Known Activations