INDEX

Explanations

the phrase "between" followed by numerical ranges

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

OGR

-0.87

gow

-0.75

rav

-0.74

eto

-0.73

vous

-0.70

jew

-0.66

 unfocusedRange

-0.63

aptic

-0.63

atically

-0.62

quished

-0.61

POSITIVE LOGITS

 halves

0.81

 sexes

0.76

 genders

0.74

 bouts

0.66

 incomes

0.65

0.63

 midnight

0.63

0.62

stocks

0.62

 extremes

0.62

Activations Density 0.027%

the phrase "between" followed by numerical ranges

No Comments

No Known Activations