INDEX

Explanations

words related to vehicle maneuvers or actions in relation to a turning motion

oai_token-act-pair · gpt-3.5-turbo

references to "turns" or "turning" in contexts involving games or vehicles

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ropolitan

-0.94

è¦ļéĨĴ

-0.91

llah

-0.78

inately

-0.70

 franc

-0.69

capacity

-0.65

mma

-0.65

gdala

-0.64

 Territories

-0.64

mble

-0.64

POSITIVE LOGITS

about

0.82

buck

0.82

turn

0.80

wheel

0.77

around

0.77

overs

0.72

undo

0.72

edit

0.70

igo

0.70

sequence

0.69

Activations Density 0.036%

words related to vehicle maneuvers or actions in relation to a turning motion

references to "turns" or "turning" in contexts involving games or vehicles

No Comments

No Known Activations