INDEX

Explanations

descriptions or summaries of various items or situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "described."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ffic

-0.84

assi

-0.75

otion

-0.72

eland

-0.72

acus

-0.72

cess

-0.70

 purse

-0.67

ggies

-0.67

externalActionCode

-0.65

vernment

-0.65

POSITIVE LOGITS

 descriptions

0.91

 describ

0.87

 described

0.85

REDACTED

0.82

 embodiments

0.80

 paragraphs

0.80

 describes

0.80

 aloud

0.77

ĸļ

0.75

 outlines

0.72

Activations Density 0.018%

descriptions or summaries of various items or situations

instances of the word "described."

No Comments

No Known Activations