INDEX

Explanations

superlatives and extremes, such as "most" or "greatest"

oai_token-act-pair · gpt-3.5-turbo

superlative adjectives indicating extreme qualities or ranks

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

é¾įåĸļå£«

-0.73

styles

-0.66

skirts

-0.65

rahim

-0.64

ancies

-0.64

 Regist

-0.64

åī

-0.63

Magic

-0.63

events

-0.63

ategor

-0.63

POSITIVE LOGITS

 conceivable

0.95

hest

0.87

 possible

0.85

est

0.82

 thing

0.81

liest

0.80

 conduit

0.77

 beneficiary

0.77

 indicator

0.77

 clue

0.77

Activations Density 0.121%

superlatives and extremes, such as "most" or "greatest"

superlative adjectives indicating extreme qualities or ranks

No Comments

No Known Activations