INDEX

Explanations

patterns or sequences of words that convey a structured meaning or order

oai_token-act-pair · gpt-3.5-turbo

references to various patterns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.76

vez

-0.73

gets

-0.69

UGE

-0.69

UGH

-0.68

ille

-0.68

zona

-0.67

rican

-0.65

ampire

-0.65

POSITIVE LOGITS

 patterns

0.92

 pattern

0.91

 Pattern

0.90

pattern

0.88

gradient

0.87

ĸļ

0.87

eering

0.86

 Patterns

0.85

Pattern

0.82

ãĤ¼ãĤ¦ãĤ¹

0.77

Activations Density 0.021%

patterns or sequences of words that convey a structured meaning or order

references to various patterns

No Comments

No Known Activations