© 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. 10-RES-JB
    11. 2714
    Prev
    Next
    INDEX
    Explanations

    phrases starting with 'a' followed by a number or 'ical'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the article "a" and related phrases that begin with the letter 'a'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ieu
    -0.71
     uncond
    -0.71
    Abs
    -0.69
    immune
    -0.69
    acid
    -0.68
    except
    -0.67
    ody
    -0.66
    rity
    -0.66
    Integ
    -0.66
    everything
    -0.65
    POSITIVE LOGITS
     recent
    1.10
     tweet
    1.08
     snippet
    1.04
     colleague
    1.01
     photograph
    1.00
     poem
    0.99
     subsequent
    0.98
     memo
    0.96
     conversation
    0.96
     nutshell
    0.95
    Activations Density 0.320%

    No Known Activations