INDEX

Explanations

terms related to directing a process in a systematic and organized manner

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "line" along with related phrases about processes or systems

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

undai

-0.97

ateurs

-0.73

rane

-0.72

oras

-0.71

 finalists

-0.69

olars

-0.69

rito

-0.67

ricular

-0.65

rum

-0.65

rit

-0.63

POSITIVE LOGITS

backer

1.24

line

1.14

lines

1.12

lined

1.00

breaks

0.90

 Lines

0.88

 Stevenson

0.85

phrine

0.83

ength

0.79

LINE

0.79

Activations Density 0.012%

terms related to directing a process in a systematic and organized manner

occurrences of the word "line" along with related phrases about processes or systems

No Comments

No Known Activations