INDEX

Explanations

adjectives related to health and wellness

oai_token-act-pair · gpt-3.5-turbo

references to health conditions and states of illness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Flavoring

-0.73

 breed

-0.61

MER

-0.61

ggles

-0.61

 delim

-0.60

Us

-0.59

Rule

-0.58

 poll

-0.58

 guid

-0.57

 href

-0.57

POSITIVE LOGITS

ridden

0.85

retty

0.82

usional

0.81

cember

0.76

angering

0.71

figured

0.70

blind

0.66

 psychiat

0.66

 enough

0.65

jured

0.65

Activations Density 0.263%

adjectives related to health and wellness

references to health conditions and states of illness

No Comments

No Known Activations