INDEX

Explanations

phrases indicating proximity or closeness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

ICAN

-0.86

AIN

-0.74

NZ

-0.73

ERG

-0.65

OOL

-0.64

urers

-0.64

onut

-0.62

uria

-0.61

rain

-0.61

Ò

-0.61

POSITIVE LOGITS

 thereto

1.08

sighted

0.97

 proximity

0.95

 enough

0.94

 minded

0.87

to

0.82

enough

0.80

 resemblance

0.76

 relatives

0.75

ups

0.72

Activations Density 0.027%

phrases indicating proximity or closeness

No Comments

No Known Activations