INDEX

Explanations

expressions of negativity or pessimism

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

Sig

-0.58

 Corpus

-0.58

 Rolls

-0.57

Dug

-0.57

 Fritz

-0.56

ITED

-0.56

 Sigma

-0.56

 Rodgers

-0.55

 supplemented

-0.55

 Rohingya

-0.55

POSITIVE LOGITS

toe

0.93

browser

0.82

desc

0.82

instance

0.82

sent

0.82

equ

0.80

inf

0.80

combat

0.79

depth

0.79

des

0.79

Activations Density 0.016%

expressions of negativity or pessimism

No Comments

No Known Activations