INDEX

Explanations

the word "Val" with varying degrees of activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Val" 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

pread

-0.84

ģĸ

-0.73

ItemTracker

-0.70

¿½

-0.65

£ı

-0.65

é¾įå¥ĳå£«

-0.64

ï¸

-0.63

 Employ

-0.63

hower

-0.63

 labor

-0.63

POSITIVE LOGITS

idation

1.27

ibr

1.11

idated

1.05

idity

1.01

ueless

1.01

ita

0.98

ulner

0.93

igon

0.92

uation

0.91

idate

0.90

Activations Density 0.010%

the word "Val" with varying degrees of activation

occurrences of the name "Val" in various contexts

No Comments

No Known Activations