INDEX

Explanations

terms related to medical conditions

oai_token-act-pair · gpt-3.5-turbo

mentions of the abbreviation "PD" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ppo

-0.89

hold

-0.83

bourg

-0.82

ãĥĦ

-0.80

ansas

-0.78

é¾įåĸļå£«

-0.76

ãĤ¤ãĥĪ

-0.73

nces

-0.72

tenance

-0.72

ãģĦ

-0.70

POSITIVE LOGITS

iamond

0.98

GF

0.95

PD

0.83

iaries

0.80

insula

0.80

ynasty

0.78

oodle

0.77

NF

0.76

illon

0.75

WD

0.74

Activations Density 0.016%

terms related to medical conditions

mentions of the abbreviation "PD" in various contexts

No Comments

No Known Activations