INDEX

Explanations

instances of the word "being" in sentences

oai_token-act-pair · gpt-3.5-turbo

the word "being" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

inav

-0.68

 Unemployment

-0.65

 constellation

-0.64

 Explosion

-0.63

Dag

-0.63

 Sinai

-0.60

 Prescott

-0.60

 Times

-0.60

Job

-0.59

PsyNetMessage

-0.58

POSITIVE LOGITS

 able

1.16

 eaten

0.89

 disposed

0.86

 seen

0.85

 judged

0.84

 considered

0.82

 undone

0.81

 treated

0.80

hemoth

0.80

held

0.79

Activations Density 0.072%

instances of the word "being" in sentences

the word "being" in various contexts

No Comments

No Known Activations