INDEX

Explanations

instances of the word "forth" in the text

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate back-and-forth movement or exchange

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 rack

-0.70

 Columb

-0.60

azo

-0.60

 Stuff

-0.59

 Roll

-0.59

 Brilliant

-0.58

 Hunting

-0.58

SEA

-0.57

 Glover

-0.56

 Jenkins

-0.56

POSITIVE LOGITS

comings

1.04

forth

1.01

rued

0.84

plain

0.83

 forth

0.82

\\\\\\\\

0.82

rance

0.80

ministic

0.79

rils

0.78

right

0.77

Activations Density 0.006%

instances of the word "forth" in the text

phrases that indicate back-and-forth movement or exchange

No Comments

No Known Activations