INDEX

Explanations

words related to toys

oai_token-act-pair · gpt-3.5-turbo

references to toys

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 transcripts

-0.77

 transcript

-0.73

idency

-0.71

inx

-0.70

ulty

-0.70

ignty

-0.68

iltration

-0.64

icago

-0.64

ornia

-0.60

 Presidency

-0.60

POSITIVE LOGITS

 toys

1.09

 dolls

1.01

toy

0.98

 Toys

0.91

 Crate

0.91

ota

0.88

Shop

0.88

box

0.88

Toy

0.86

bucks

0.85

Activations Density 0.073%

words related to toys

references to toys

No Comments

No Known Activations