INDEX

Explanations

instances of positive sentiment or favorable evaluations

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

ãĤ©

-0.84

prise

-0.79

lar

-0.76

ãĥĪ

-0.73

anium

-0.72

mington

-0.69

 Goff

-0.68

lon

-0.68

ning

-0.68

xton

-0.68

POSITIVE LOGITS

/-

1.11

 IMAGES

1.08

/+

0.68

#$

0.67

%.

0.66

 intersections

0.65

ileged

0.64

 crossings

0.63

 editions

0.61

TIT

0.61

Activations Density 0.006%

instances of positive sentiment or favorable evaluations

No Comments

No Known Activations