INDEX

Explanations

keywords associated with a selection or choice process

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Select" and related forms

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

FORE

-0.69

STD

-0.68

 nerv

-0.66

nz

-0.66

orah

-0.64

bye

-0.62

ipple

-0.62

WARN

-0.62

BIP

-0.61

Wa

-0.61

POSITIVE LOGITS

ivity

1.18

ively

1.06

ives

0.89

ions

0.80

cuts

0.80

inations

0.79

ivities

0.77

prising

0.76

lime

0.74

prises

0.73

Activations Density 0.023%

keywords associated with a selection or choice process

occurrences of the word "Select" and related forms

No Comments

No Known Activations