INDEX

Explanations

mentions of the name "Wilson"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Wilson"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

plate

-0.82

Rated

-0.78

aft

-0.77

awaru

-0.75

abetic

-0.74

URI

-0.73

angular

-0.71

otten

-0.69

ammy

-0.68

unal

-0.68

POSITIVE LOGITS

 Wilson

0.89

ston

0.86

 Norton

0.85

 Chandler

0.84

ufact

0.79

sey

0.78

 Kenobi

0.76

ville

0.75

hawk

0.75

hawks

0.72

Activations Density 0.015%

mentions of the name "Wilson"

occurrences of the name "Wilson"

No Comments

No Known Activations