INDEX

Explanations

phrases related to hiding or concealing something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Hide" or variations, indicating a focus on concealment or obfuscation in the text

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

etheless

-0.90

odic

-0.85

ammy

-0.78

ionic

-0.77

ilingual

-0.77

eele

-0.76

ulz

-0.74

iod

-0.72

theless

-0.72

bably

-0.71

POSITIVE LOGITS

 Caption

1.04

 Hide

0.99

Hide

0.97

away

0.97

ously

0.72

Emb

0.69

ãĥĥãĥī

0.69

Pic

0.69

hide

0.68

Track

0.68

Activations Density 0.011%

phrases related to hiding or concealing something

instances of the word "Hide" or variations, indicating a focus on concealment or obfuscation in the text

No Comments

No Known Activations