INDEX

Explanations

words related to medical conditions and treatments, especially surgery and injuries

oai_token-act-pair · gpt-3.5-turbo

words related to bodily functions and processes

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

shore

-0.71

 genders

-0.69

 leash

-0.61

sight

-0.60

 fact

-0.59

endor

-0.58

 reins

-0.57

hens

-0.57

PUT

-0.57

 Cherokee

-0.56

POSITIVE LOGITS

berus

1.15

cer

0.99

oute

0.90

ozo

0.89

ulent

0.85

culus

0.84

nel

0.84

pillar

0.83

ate

0.82

anos

0.81

Activations Density 0.031%

words related to medical conditions and treatments, especially surgery and injuries

words related to bodily functions and processes

No Comments

No Known Activations