INDEX

Explanations

information about winning or achieving success

oai_token-act-pair · gpt-3.5-turbo

numerical statistics related to events or achievements

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

)—

-0.65

stakes

-0.61

Ãĥ

-0.59

Ħ¢

-0.59

ifestyle

-0.58

 Yourself

-0.57

 ÂŃ

-0.55

VICE

-0.55

Enlarge

-0.54

!--

-0.54

POSITIVE LOGITS

 likewise

0.80

 meanwhile

0.78

 theirs

0.77

 similarly

0.75

 similar

0.73

tho

0.72

pts

0.69

 precedence

0.67

 Same

0.65

 whereas

0.64

Activations Density 1.474%

information about winning or achieving success

numerical statistics related to events or achievements

No Comments

No Known Activations