INDEX

Explanations

phrases related to following instructions or guidelines

oai_token-act-pair · gpt-3.5-turbo

terms related to instructions and specifications 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Opportun

-0.65

duc

-0.62

whel

-0.60

\\\\\\\\

-0.59

 srfAttach

-0.59

noxious

-0.59

entimes

-0.58

Status

-0.58

 Bucks

-0.57

ski

-0.57

POSITIVE LOGITS

 themselves

1.28

etter

1.09

etting

1.07

pace

1.03

heet

1.02

creen

1.00

hift

0.98

mith

0.97

 necessary

0.95

peed

0.91

Activations Density 0.337%

phrases related to following instructions or guidelines

terms related to instructions and specifications in various contexts

No Comments

No Known Activations