INDEX

Explanations

incidents or events involving negative actions or consequences related to individuals

oai_token-act-pair · gpt-3.5-turbo

the word "after" indicating sequences of events or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

aez

-0.94

tick

-0.80

Mask

-0.78

DragonMagazine

-0.77

achel

-0.74

Near

-0.72

eous

-0.71

cin

-0.71

NRS

-0.71

âĸĪâĸĪâĸĪâĸĪ

-0.70

POSITIVE LOGITS

 completing

0.88

 discovering

0.87

 inspecting

0.84

noon

0.83

 failing

0.83

 midnight

0.83

 sustaining

0.82

 spotting

0.82

 sunset

0.82

 acquiring

0.81

Activations Density 0.098%

incidents or events involving negative actions or consequences related to individuals

the word "after" indicating sequences of events or incidents

No Comments

No Known Activations