INDEX

Explanations

numbers representing time durations

oai_token-act-pair · gpt-3.5-turbo

occurrences of time durations in minutes

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

sonian

-0.79

raviolet

-0.75

spons

-0.74

Mars

-0.72

DragonMagazine

-0.70

igm

-0.67

keye

-0.66

wealth

-0.66

Las

-0.66

SON

-0.66

POSITIVE LOGITS

ftime

0.75

 stopp

0.73

 Hate

0.68

 Subst

0.67

Ago

0.66

 played

0.66

 scoring

0.65

 opener

0.65

 coached

0.64

 halftime

0.64

Activations Density 0.030%

numbers representing time durations

occurrences of time durations in minutes

No Comments

No Known Activations