INDEX

Explanations

terms related to the term 'add' with varying activation levels

oai_token-act-pair · gpt-3.5-turbo

the term "add" in various contexts or constructions

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

tem

-0.71

ãĥīãĥ©ãĤ´ãĥ³

-0.68

bane

-0.68

Consumer

-0.66

âĸ¬

-0.65

 exha

-0.64

Â·Â·

-0.63

externalActionCode

-0.61

 Maker

-0.60

PLAY

-0.60

POSITIVE LOGITS

icted

1.28

itional

1.21

itionally

1.20

iction

1.14

icts

1.14

resses

1.14

ition

1.13

ictive

1.05

ressed

1.05

ened

1.05

Activations Density 0.021%

terms related to the term 'add' with varying activation levels

the term "add" in various contexts or constructions

No Comments

No Known Activations