INDEX

Explanations

mentions of the word "post" followed by a number, possibly related to a time period or specific event

oai_token-act-pair · gpt-3.5-turbo

references to post-event conditions or states

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Qiao

-0.91

ï¸

-0.77

ï¸ı

-0.76

 Orchestra

-0.76

owship

-0.76

 Bett

-0.75

 Faul

-0.72

 Fitz

-0.72

 Lauder

-0.71

aughs

-0.70

POSITIVE LOGITS

gres

1.33

doctoral

1.23

hum

1.19

mortem

1.18

modern

1.16

natal

1.08

graduate

1.04

ulates

1.03

docs

1.03

ulated

1.01

Activations Density 0.038%

mentions of the word "post" followed by a number, possibly related to a time period or specific event

references to post-event conditions or states

No Comments

No Known Activations