INDEX

Explanations

phrases that introduce findings or conclusions from reports or studies

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

Newsletter

-0.81

-0.79

lihood

-0.69

 Incident

-0.65

efer

-0.64

ItemThumbnailImage

-0.63

gallery

-0.63

ecause

-0.61

ItemImage

-0.61

beer

-0.60

POSITIVE LOGITS

 watchdog

0.81

 bombshell

0.64

 scathing

0.64

new

0.62

 damning

0.62

 experts

0.62

 landmark

0.60

ptroller

0.59

 strugg

0.59

PROV

0.59

Activations Density 0.142%

phrases that introduce findings or conclusions from reports or studies

No Comments

No Known Activations

phrases that introduce findings or conclusions from reports or studies

No Comments

No Known Activations