INDEX

Explanations

the word "amb" with varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

instances of the token "amb" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

naires

-0.77

backer

-0.74

kies

-0.71

creen

-0.71

Downloadha

-0.70

terday

-0.68

housing

-0.68

ãĥīãĥ©

-0.66

spection

-0.66

 suspicion

-0.66

POSITIVE LOGITS

ilib

1.04

assador

1.02

odies

0.90

assadors

0.90

ilit

0.87

rill

0.87

alo

0.86

uilding

0.84

olic

0.83

ulative

0.82

Activations Density 0.019%

the word "amb" with varying levels of activation

instances of the token "amb" in various contexts

No Comments

No Known Activations