INDEX

Explanations

phrases related to military or police operations

oai_token-act-pair · gpt-3.5-turbo

references to various operations or missions

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

aez

-0.79

arton

-0.77

hus

-0.76

hner

-0.71

bitious

-0.71

cknowled

-0.66

eree

-0.65

yi

-0.65

ingers

-0.65

haw

-0.64

POSITIVE LOGITS

ally

0.94

ional

0.93

eering

0.92

ality

0.83

 undertaken

0.81

ions

0.74

 conducted

0.74

ãĥ¢

0.73

 Werewolf

0.72

 Twist

0.72

Activations Density 0.023%

phrases related to military or police operations

references to various operations or missions

No Comments

No Known Activations