INDEX

Explanations

phrases mentioning statistical relationships or connections between different variables

oai_token-act-pair · gpt-3.5-turbo

statements regarding statistical correlations

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

mbuds

-0.70

imm

-0.66

gm

-0.65

wagen

-0.65

sk

-0.65

OWN

-0.62

scrib

-0.61

disk

-0.60

AND

-0.59

Cmd

-0.59

POSITIVE LOGITS

 coefficient

1.15

SHIP

1.06

 coefficients

0.98

 between

0.97

between

0.95

 Between

0.94

 linking

0.89

 correlation

0.88

alogy

0.83

ology

0.82

Activations Density 0.044%

phrases mentioning statistical relationships or connections between different variables

statements regarding statistical correlations

No Comments

No Known Activations