INDEX

Explanations

references to specific timeframes in the past

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "last" in various contexts related to time

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

ourge

-0.72

cius

-0.67

cil

-0.66

riott

-0.65

lectic

-0.61

ipation

-0.57

xual

-0.57

pherd

-0.56

ription

-0.56

oute

-0.55

POSITIVE LOGITS

 week

0.92

fm

0.87

 year

0.78

ebin

0.77

STEP

0.77

 rites

0.74

week

0.74

Week

0.72

 weekend

0.71

yr

0.71

Activations Density 0.064%

references to specific timeframes in the past

occurrences of the word "last" in various contexts related to time

No Comments

No Known Activations