INDEX

Explanations

phrases related to beliefs or assumptions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "to" indicating intention or belief

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

river

-0.77

noticed

-0.66

bats

-0.65

case

-0.64

 Perspective

-0.64

 viewer

-0.61

 Rapids

-0.61

 Spaces

-0.60

finder

-0.60

iott

-0.60

POSITIVE LOGITS

be

1.04

 embody

0.96

 originate

0.92

 indicate

0.91

 derive

0.89

 resemble

0.89

 belong

0.89

 signify

0.87

 have

0.87

 imply

0.86

Activations Density 0.110%

phrases related to beliefs or assumptions

occurrences of the word "to" indicating intention or belief

No Comments

No Known Activations