INDEX

Explanations

phrases indicating indecision or uncertainty about what action to take

oai_token-act-pair · gpt-3.5-turbo

the phrase "what to do"

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

Kau

-0.61

ndra

-0.58

prints

-0.57

ioxide

-0.57

Constructed

-0.56

 Prosper

-0.55

 Plum

-0.54

Used

-0.54

 Rivals

-0.54

eatures

-0.53

POSITIVE LOGITS

 differently

1.09

 next

1.06

 about

0.99

 ABOUT

0.92

 NEXT

0.86

 with

0.80

if

0.79

omb

0.79

pez

0.78

omsday

0.76

Activations Density 0.059%

phrases indicating indecision or uncertainty about what action to take

the phrase "what to do"

No Comments

No Known Activations