INDEX

Explanations

issues related to judgment and self-perception in contexts of mistakes or failures

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

 Canaver

-0.73

ricanes

-0.67

 Colomb

-0.67

 Crom

-0.65

gypt

-0.63

 Franch

-0.61

 NYPD

-0.58

outhern

-0.58

 Coulter

-0.57

 shotguns

-0.57

POSITIVE LOGITS

 improvement

0.74

 stimulus

0.73

 payoff

0.71

 progress

0.70

)).

0.70

worthiness

0.69

 satisf

0.69

 flaw

0.69

Completed

0.69

etc

0.68

Activations Density 0.511%

issues related to judgment and self-perception in contexts of mistakes or failures

No Comments

No Known Activations