INDEX

Explanations

words related to medical conditions or diseases ending in '-roph' or '-rophic'

oai_token-act-pair · gpt-3.5-turbo

terms related to specific medical conditions and biology

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

bell

-0.81

lift

-0.76

maid

-0.75

ãĤ´ãĥ³

-0.74

que

-0.73

ports

-0.73

pent

-0.71

pee

-0.65

creen

-0.63

 Marqu

-0.63

POSITIVE LOGITS

reens

0.85

roup

0.81

roups

0.79

udence

0.79

raham

0.77

uild

0.76

stals

0.74

sts

0.72

unctions

0.71

raphics

0.70

Activations Density 0.080%

words related to medical conditions or diseases ending in '-roph' or '-rophic'

terms related to specific medical conditions and biology

No Comments

No Known Activations