INDEX

Explanations

the word "little" preceded by another word

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "little."

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

itivity

-0.81

igham

-0.77

CoC

-0.72

rite

-0.70

anwhile

-0.66

zanne

-0.66

idon

-0.65

rette

-0.64

eneg

-0.64

idents

-0.64

POSITIVE LOGITS

bit

0.85

kid

0.68

thing

0.67

legged

0.66

tid

0.66

 patience

0.65

 girls

0.65

 avail

0.64

finger

0.64

 girl

0.64

Activations Density 0.025%

the word "little" preceded by another word

occurrences of the word "little."

No Comments

No Known Activations