INDEX

Explanations

forms of the verb "to be" in various tenses

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

 Frazier

-0.74

 sqor

-0.69

iggins

-0.66

rities

-0.64

onds

-0.64

LIN

-0.63

 Awakens

-0.62

 attest

-0.61

yip

-0.61

 Ingredients

-0.61

POSITIVE LOGITS

forth

0.97

 able

0.93

 chosen

0.90

 singled

0.82

 supposed

0.80

 bothered

0.79

 compelled

0.79

named

0.78

 bothering

0.77

 drawn

0.76

Activations Density 0.069%

forms of the verb "to be" in various tenses

No Comments

No Known Activations