INDEX

Explanations

substrings with the word "of"

oai_token-act-pair · gpt-3.5-turbo

references to measurements and statistical margins of error

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

roots

-0.83

fml

-0.79

HF

-0.78

bats

-0.70

nw

-0.69

iov

-0.68

pots

-0.66

sites

-0.66

mr

-0.65

 Aires

-0.64

POSITIVE LOGITS

 occurrence

1.03

 descent

1.02

 ascent

1.01

 advancement

1.00

 change

0.96

 departure

0.96

 return

0.95

 entry

0.94

 improvement

0.92

 rotation

0.90

Activations Density 0.084%

substrings with the word "of"

references to measurements and statistical margins of error

No Comments

No Known Activations