INDEX

Explanations

profound or impactful statements

oai_token-act-pair · gpt-3.5-turbo

frequent occurrences or references to sources

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

 withd

-0.90

 cabbage

-0.82

 challeng

-0.82

 inver

-0.80

 brut

-0.80

 attacker

-0.78

 fermented

-0.78

 flowering

-0.77

 crabs

-0.76

 mosqu

-0.76

POSITIVE LOGITS

 Accessed

1.26

jpg

1.15

 Retrieved

1.15

Org

1.11

org

1.08

txt

1.01

pdf

0.95

com

0.92

 Contains

0.92

png

0.92

Activations Density 0.242%

profound or impactful statements

frequent occurrences or references to sources

No Comments

No Known Activations