INDEX

Explanations

words related to counting or numerical values

oai_token-act-pair · gpt-3.5-turbo

instances of the word "count" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 misunder

-0.75

insula

-0.71

 obser

-0.71

 constitu

-0.67

 Harbor

-0.64

 conditioning

-0.60

agar

-0.60

ieties

-0.60

antha

-0.59

 landfall

-0.58

POSITIVE LOGITS

enance

1.97

downs

1.10

ries

1.02

esses

0.95

ess

0.93

rified

0.91

down

0.89

ENCY

0.80

tops

0.79

ere

0.79

Activations Density 0.050%

words related to counting or numerical values

instances of the word "count" and its variations

No Comments

No Known Activations