INDEX

Explanations

phrases related to hoarding behavior

oai_token-act-pair · gpt-3.5-turbo

phrases related to the word "ho" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Annotations

-0.82

 Norn

-0.75

 Sacrament

-0.73

 GOODMAN

-0.73

é»Ĵ

-0.72

 Clause

-0.72

 Consent

-0.68

 Proceedings

-0.68

ãĤ±

-0.68

 Pyramid

-0.68

POSITIVE LOGITS

arding

1.29

ppy

1.14

eful

1.12

vel

1.10

efully

1.09

oping

1.08

ogie

1.07

isted

1.02

ving

1.01

arded

1.01

Activations Density 0.006%

phrases related to hoarding behavior

phrases related to the word "ho" in various contexts

No Comments

No Known Activations