INDEX

Explanations

the word "se" with various endings

oai_token-act-pair · gpt-3.5-turbo

the word "see" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

initely

-0.80

INGTON

-0.77

ashtra

-0.73

enegger

-0.73

enhagen

-0.72

 hoops

-0.72

SHIP

-0.69

£ı

-0.69

eanor

-0.68

etheless

-0.68

POSITIVE LOGITS

eps

1.04

vel

0.96

perate

0.95

ve

0.94

leanor

0.92

xt

0.91

wed

0.91

rend

0.90

eker

0.90

vent

0.89

Activations Density 0.012%

the word "se" with various endings

the word "see" in various contexts

No Comments

No Known Activations