INDEX

Explanations

phrases related to being separate or different from a larger group or entity

oai_token-act-pair · gpt-3.5-turbo

instances of the word "separate."

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

=-=-=-=-=-=-=-=-

-0.77

enos

-0.73

Ö¼

-0.70

 âī¡

-0.70

 Almighty

-0.70

 Beans

-0.69

âĺħâĺħ

-0.67

WARD

-0.65

 Briggs

-0.65

OLD

-0.65

POSITIVE LOGITS

 separate

0.96

 detach

0.87

 halves

0.86

 sexes

0.84

inguished

0.82

secondary

0.79

 separ

0.76

iating

0.75

iations

0.75

icut

0.75

Activations Density 0.010%

phrases related to being separate or different from a larger group or entity

instances of the word "separate."

No Comments

No Known Activations