INDEX

Explanations

numerical references to time frames or durations

oai_token-act-pair · gpt-3.5-turbo

terms related to time spans and durations

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

éĥ

-0.74

«

-0.62

 pione

-0.61

èĪ

-0.61

æķ

-0.60

è£ħ

-0.60

å¤

-0.59

Ħ

-0.58

è»

-0.57

çļ

-0.57

POSITIVE LOGITS

 causation

0.58

 disclaimer

0.56

 scrimmage

0.54

 standings

0.53

 timetable

0.53

 divid

0.52

dule

0.52

 schedules

0.52

 dividing

0.52

 timelines

0.51

Activations Density 1.819%

numerical references to time frames or durations

terms related to time spans and durations

No Comments

No Known Activations