INDEX

Explanations

questions or statements indicating a need for action or resolution

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate necessity or requirement for action

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

gdala

-0.72

Zip

-0.65

 Democr

-0.64

 Rost

-0.62

izon

-0.62

 Mamm

-0.61

 Guilty

-0.59

 Varg

-0.57

theless

-0.56

ulty

-0.56

POSITIVE LOGITS

 attention

0.94

lessly

0.91

 scrutiny

0.82

FINE

0.77

 tweaking

0.77

ENTION

0.75

 updating

0.75

 Citation

0.73

 correction

0.72

 refinement

0.72

Activations Density 0.078%

questions or statements indicating a need for action or resolution

phrases that indicate necessity or requirement for action

No Comments

No Known Activations