INDEX

Explanations

negative sentiment or criticism

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

 stoked

-0.63

 Sultan

-0.61

lax

-0.60

 convol

-0.60

 ranks

-0.59

lement

-0.57

ISTER

-0.56

 wedd

-0.56

 Archdemon

-0.55

 stagn

-0.55

POSITIVE LOGITS

purpose

0.80

sight

0.78

task

0.76

oeuv

0.76

each

0.76

package

0.76

die

0.75

sent

0.74

street

0.74

one

0.74

Activations Density 0.015%

negative sentiment or criticism

No Comments

No Known Activations