© 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. 24110
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names or terms with the letter 'R'

    oai_token-act-pair · gpt-3.5-turbo

    the letter "R" in various contexts

    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
    ãĥ¼ãĥĨãĤ£
    -0.77
    glers
    -0.76
    terson
    -0.74
     Nieto
    -0.73
     Virtue
    -0.73
     CPR
    -0.72
    lihood
    -0.71
    -+-+
    -0.70
     Totem
    -0.70
     Corpus
    -0.68
    POSITIVE LOGITS
    ansom
    1.23
    ascal
    1.17
    haps
    1.13
    senal
    1.12
    enn
    1.06
    outine
    1.05
    ework
    1.02
    ach
    1.02
    aul
    1.01
    acing
    1.00
    Activations Density 0.052%

    No Known Activations