INDEX

Explanations

patterns or sequences of words

oai_token-act-pair · gpt-3.5-turbo

references to patterns and pattern recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

omez

-0.80

ascular

-0.77

vez

-0.70

UGH

-0.69

rican

-0.68

zona

-0.68

orean

-0.66

ille

-0.66

gets

-0.65

UGE

-0.65

POSITIVE LOGITS

 pattern

0.92

 patterns

0.92

 Pattern

0.91

pattern

0.89

Pattern

0.87

gradient

0.86

 Patterns

0.86

ĸļ

0.81

eering

0.80

 repeats

0.78

Activations Density 0.032%

patterns or sequences of words

references to patterns and pattern recognition

No Comments

No Known Activations