INDEX

Explanations

occurrences of the word "rotation" 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hig

-0.84

asper

-0.79

raq

-0.79

omething

-0.75

eteria

-0.73

hiro

-0.73

native

-0.71

abba

-0.71

ãĤ¨ãĥ«

-0.70

ãģį

-0.70

POSITIVE LOGITS

ary

0.90

 rotation

0.90

 axis

0.86

 direction

0.82

ally

0.82

 rotating

0.78

 wrench

0.74

 lock

0.72

 gears

0.71

 revolutions

0.70

Activations Density 0.007%

occurrences of the word "rotation" and its variations

No Comments

No Known Activations