INDEX

Explanations

adjectives or verbs related to expectations

oai_token-act-pair · gpt-3.5-turbo

phrases expressing expectations or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

packing

-0.73

SPONSORED

-0.70

amic

-0.69

matter

-0.68

 Physics

-0.68

false

-0.67

founded

-0.66

issy

-0.66

Program

-0.64

null

-0.63

POSITIVE LOGITS

 expect

1.07

 expects

0.80

 vulner

0.80

eur

0.79

ĳå£«

0.76

IELD

0.76

terson

0.72

ĭ

0.72

ricanes

0.72

 adolesc

0.71

Activations Density 0.017%

adjectives or verbs related to expectations

phrases expressing expectations or predictions

No Comments

No Known Activations