INDEX

Explanations

instances of the word "assign" with varying levels of importance

oai_token-act-pair · gpt-3.5-turbo

words related to assigning or interpreting actions and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Feeling

-0.71

Downloadha

-0.64

ItemTracker

-0.63

 Peninsula

-0.60

Ain

-0.59

 Archangel

-0.59

REDACTED

-0.58

existent

-0.57

 brow

-0.57

 towed

-0.57

POSITIVE LOGITS

ings

1.55

ments

1.53

ables

1.30

able

1.26

ties

1.23

orate

1.17

ingly

1.16

ively

1.13

ations

1.12

itures

1.10

Activations Density 0.105%

instances of the word "assign" with varying levels of importance

words related to assigning or interpreting actions and responsibilities

No Comments

No Known Activations