INDEX

Explanations

lines related to document formatting and code syntax errors

oai_token-act-pair · gpt-3.5-turbo

specific jargon or terminology related to selections, items, and classifications

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bably

-0.76

otrop

-0.72

 Dunn

-0.72

©¶æ

-0.68

-0.67

stad

-0.67

hon

-0.65

raz

-0.63

bon

-0.63

erb

-0.62

POSITIVE LOGITS

1.05

:#

0.95

::

0.83

.:

0.82

:'

0.79

:,

0.79

:-

0.79

iculty

0.74

 Fiat

0.69

 eurozone

0.66

Activations Density 0.148%

lines related to document formatting and code syntax errors

specific jargon or terminology related to selections, items, and classifications

No Comments

No Known Activations