INDEX

Explanations

patterns of characters that do not form recognizable words or phrases, potentially related to noise or coding errors

oai_token-act-pair · gpt-3.5-turbo

specific character sequences or symbols

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

ighed

-0.91

iscal

-0.82

idges

-0.75

igon

-0.75

oche

-0.74

iche

-0.72

cients

-0.72

Phi

-0.70

 Siem

-0.69

elsen

-0.69

POSITIVE LOGITS

ãģ

1.26

ãĤī

1.20

ãĤĮ

1.17

ãģĭ

1.14

ãĤĭ

1.13

ãģĵ

1.10

ãģĦ

1.06

ãĤ

1.06

ãģ£

1.05

ãģķ

1.05

Activations Density 0.014%

patterns of characters that do not form recognizable words or phrases, potentially related to noise or coding errors

specific character sequences or symbols

No Comments

No Known Activations