INDEX

Explanations

words related to fear or causing fear

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "scare" in various contexts

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

•layer 7 - fear

No Comments

Negative Logits

iciency

-0.76

cially

-0.72

 arrang

-0.71

ional

-0.69

entials

-0.69

edded

-0.67

 enriched

-0.66

ibble

-0.66

odore

-0.66

tein

-0.65

POSITIVE LOGITS

crow

1.87

mong

1.29

warts

0.86

ingly

0.80

faced

0.76

vana

0.74

Cry

0.74

bite

0.74

escape

0.71

 Nikki

0.70

Activations Density 0.029%

words related to fear or causing fear

occurrences of the word "scare" in various contexts

No Comments

No Known Activations