INDEX

Explanations

phrases containing the word "by" indicating attribution or authorship

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

isms

-0.81

hops

-0.77

idences

-0.77

worthiness

-0.73

database

-0.73

zone

-0.72

leeve

-0.72

uality

-0.70

bra

-0.70

olate

-0.69

POSITIVE LOGITS

Ay

0.92

 Todd

0.91

 Christine

0.88

 Stephen

0.87

 Ellen

0.86

 Richard

0.85

Tom

0.85

 Yosh

0.83

 former

0.83

 Shinzo

0.83

Activations Density 0.032%

phrases containing the word "by" indicating attribution or authorship

No Comments

No Known Activations