INDEX

Explanations

past tense verbs ending in 'ed'

oai_token-act-pair · gpt-3.5-turbo

expressions of realization or understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

osures

-0.65

 Britann

-0.61

 injunction

-0.61

prev

-0.60

picking

-0.59

Topic

-0.59

bey

-0.58

acco

-0.58

ĪĴ

-0.57

ciating

-0.56

POSITIVE LOGITS

ledged

0.92

how

0.89

ibility

0.74

urities

0.73

ually

0.73

ledge

0.73

omething

0.73

REAM

0.72

âĶģ

0.71

why

0.71

Activations Density 0.040%

past tense verbs ending in 'ed'

expressions of realization or understanding

No Comments

No Known Activations