INDEX

Explanations

mentions of historical figures and locations associated with architecture or literature

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

erence

-0.81

pos

-0.73

ence

-0.73

inez

-0.72

riter

-0.72

cel

-0.70

ilater

-0.70

lÃ©

-0.70

pelled

-0.69

meric

-0.69

POSITIVE LOGITS

 Basin

0.80

0.75

 basin

0.73

Jur

0.70

opt

0.64

âĶĢâĶĢâĶĢâĶĢ

0.64

 Cities

0.63

 Warden

0.62

 Polk

0.61

OPS

0.61

Activations Density 0.016%

mentions of historical figures and locations associated with architecture or literature

No Comments

No Known Activations