INDEX

Explanations

words related to stress

oai_token-act-pair · gpt-4-turbo

words related to stress

oai_token-act-pair · gpt-3.5-turbo

repeated references to stress

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

izons

-0.82

VICE

-0.69

HCR

-0.69

Aust

-0.67

axies

-0.66

*/(

-0.65

ettes

-0.64

gewater

-0.64

kie

-0.64

gom

-0.63

POSITIVE LOGITS

stress

0.94

 stress

0.88

 reliever

0.85

ors

0.85

 Stress

0.85

âĶģ

0.81

 cooker

0.78

urer

0.77

imaru

0.76

ively

0.75

Activations Density 0.008%

words related to stress

words related to stress

repeated references to stress

No Comments

No Known Activations