INDEX

Explanations

instances of words related to running or moving quickly

oai_token-act-pair · gpt-3.5-turbo

instances of the words "run" and "ran."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lauder

-0.68

repre

-0.66

theless

-0.63

alam

-0.60

 suscept

-0.59

olia

-0.58

iasco

-0.58

 defic

-0.58

ortium

-0.57

 subsequ

-0.57

POSITIVE LOGITS

escape

1.01

aways

0.97

gs

0.93

af

0.89

away

0.85

nin

0.83

agate

0.81

dy

0.80

 rampant

0.80

around

0.79

Activations Density 0.049%

instances of words related to running or moving quickly

instances of the words "run" and "ran."

No Comments

No Known Activations