INDEX

Explanations

technical terms and abbreviations

oai_token-act-pair · gpt-3.5-turbo

parentheses or punctuation marks in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 treasury

-0.73

ilee

-0.68

 contrace

-0.62

lish

-0.62

ified

-0.62

Gur

-0.62

itiz

-0.61

 inspecting

-0.61

 eyeb

-0.61

 engagement

-0.60

POSITIVE LOGITS

ï¸

0.79

pmwiki

0.77

 Unloaded

0.75

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.75

RESULTS

0.72

 Characters

0.72

âķ

0.71

[+

0.70

BILITIES

0.70

âķĲ

0.70

Activations Density 0.089%

technical terms and abbreviations

parentheses or punctuation marks in sentences

No Comments

No Known Activations