INDEX

Explanations

the presence of the word "mind" in various forms and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

 Mehran

-0.79

HH

-0.71

 sever

-0.66

 KING

-0.64

 excise

-0.64

ATED

-0.61

Filename

-0.61

Reviewed

-0.60

interstitial

-0.60

TAIN

-0.60

POSITIVE LOGITS

fulness

1.42

ful

1.23

bender

1.09

storms

1.00

iac

0.99

fully

0.95

scape

0.95

spring

0.87

sets

0.86

sworth

0.86

Activations Density 0.006%

the presence of the word "mind" in various forms and contexts

No Comments

No Known Activations