INDEX

Explanations

the title of movies within a sentence

oai_token-act-pair · gpt-3.5-turbo

quotation marks in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 matter

-0.83

 grasp

-0.75

 batter

-0.73

 pity

-0.73

peg

-0.72

 pillar

-0.72

 barr

-0.72

 prag

-0.72

 affiliate

-0.70

 prey

-0.69

POSITIVE LOGITS

Big

1.19

Morning

1.19

their

1.15

Friends

1.14

Operation

1.14

Untitled

1.13

Bad

1.13

classic

1.12

Golden

1.12

Ultimate

1.11

Activations Density 0.089%

the title of movies within a sentence

quotation marks in the text

No Comments

No Known Activations