INDEX

Explanations

words related to negative feelings such as loathing

oai_token-act-pair · gpt-3.5-turbo

instances of the word "loathe" in various forms and context

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

rition

-0.83

rity

-0.76

pillar

-0.75

manship

-0.72

ITAL

-0.71

lished

-0.71

glass

-0.70

 Norn

-0.70

TAIN

-0.68

race

-0.66

POSITIVE LOGITS

oser

1.09

aves

1.06

veland

1.04

aning

1.03

fty

1.03

vers

0.94

aned

0.94

zzle

0.93

vel

0.91

zz

0.91

Activations Density 0.015%

words related to negative feelings such as loathing

instances of the word "loathe" in various forms and context

No Comments

No Known Activations