INDEX

Explanations

occurrences of the word "word" and its variations

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

idences

-0.74

illac

-0.71

hematic

-0.68

itant

-0.68

ĸļ

-0.67

avorite

-0.66

iery

-0.65

kens

-0.65

":[{"

-0.64

alus

-0.64

POSITIVE LOGITS

press

0.93

 regarding

0.76

lings

0.75

print

0.70

 about

0.68

sworth

0.67

boys

0.66

mark

0.66

 concerning

0.66

boats

0.65

Activations Density 0.009%

occurrences of the word "word" and its variations

No Comments

No Known Activations