INDEX

Explanations

objects or elements that are described as being attached or connected

oai_token-act-pair · gpt-3.5-turbo

the word "that" in various contexts and its grammatical usage

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

ODY

-0.71

done

-0.70

KNOWN

-0.66

 Expect

-0.66

 interviewing

-0.63

icularly

-0.60

 minded

-0.59

ONE

-0.59

 Checking

-0.59

 expectation

-0.58

POSITIVE LOGITS

 resembles

1.26

 attaches

1.25

 protr

1.18

 sits

1.14

 separates

1.14

 corresponds

1.13

 absorbs

1.12

 connects

1.11

 protects

1.11

 emits

1.10

Activations Density 0.157%

objects or elements that are described as being attached or connected

the word "that" in various contexts and its grammatical usage

No Comments

No Known Activations