INDEX

Explanations

instances of the word "did."

oai_token-act-pair · gpt-3.5-turbo

the word "did" and its variations indicating actions performed

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

case

-0.68

liner

-0.68

stood

-0.68

washer

-0.66

 Methods

-0.66

 Handling

-0.66

fields

-0.65

bent

-0.65

arb

-0.64

 Offense

-0.63

POSITIVE LOGITS

actic

1.04

pez

0.97

 confir

0.81

oms

0.81

 manage

0.81

 indeed

0.79

not

0.79

ĸļ

0.78

ppel

0.74

nt

0.74

Activations Density 0.077%

instances of the word "did."

the word "did" and its variations indicating actions performed

No Comments

No Known Activations