INDEX

Explanations

phrases related to going back or returning to a previous state or location

oai_token-act-pair · gpt-3.5-turbo

references to returning to a previous state or situation

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

yre

-0.61

 Consent

-0.60

stood

-0.60

orst

-0.57

VICE

-0.54

anooga

-0.54

Merit

-0.53

Ire

-0.52

olulu

-0.52

 Catch

-0.51

POSITIVE LOGITS

packing

1.16

stab

1.06

tracking

1.03

gam

0.99

packs

0.98

track

0.94

doors

0.89

door

0.89

wards

0.86

stairs

0.85

Activations Density 0.028%

phrases related to going back or returning to a previous state or location

references to returning to a previous state or situation

No Comments

No Known Activations