INDEX

Explanations

words or phrases related to sticking or holding on

oai_token-act-pair · gpt-3.5-turbo

expressions related to attachment and dependency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

oker

-0.68

ufact

-0.66

ibel

-0.64

Rated

-0.64

BLIC

-0.61

cloth

-0.61

FORE

-0.60

taining

-0.60

plan

-0.60

ãĥ£

-0.60

POSITIVE LOGITS

 cling

1.24

 clinging

0.91

 onto

0.85

rily

0.80

 uncond

0.77

 pigeon

0.74

 welf

0.74

 confinement

0.71

shell

0.71

attach

0.71

Activations Density 0.025%

words or phrases related to sticking or holding on

expressions related to attachment and dependency

No Comments

No Known Activations