INDEX

Explanations

numerical patterns representing years

oai_token-act-pair · gpt-3.5-turbo

references to specific years and historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ndra

-0.66

Tu

-0.63

edge

-0.63

seed

-0.62

Sensor

-0.59

Edge

-0.59

holder

-0.58

jriwal

-0.58

ledged

-0.56

 causal

-0.56

POSITIVE LOGITS

ĸļ

0.90

-'

0.87

ãĥŁ

0.85

å¹

0.81

ãĤ¦ãĤ¹

0.69

 Newsweek

0.68

 onwards

0.66

BCE

0.66

chev

0.65

âķĲ

0.63

Activations Density 0.068%

numerical patterns representing years

references to specific years and historical events

No Comments

No Known Activations