INDEX

Explanations

numeric values, rankings, and statistics mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

quantitative metrics and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

iscovery

-0.69

arie

-0.68

iscover

-0.67

Ã§

-0.65

enment

-0.64

icer

-0.64

redo

-0.63

iday

-0.62

gae

-0.60

apy

-0.60

POSITIVE LOGITS

minimum

0.81

 percentages

0.79

 Percentage

0.73

verages

0.72

 percentage

0.72

 guiActiveUnfocused

0.72

Minimum

0.71

 coefficients

0.70

 totals

0.70

 probabilities

0.69

Activations Density 1.084%

numeric values, rankings, and statistics mentioned in the text

quantitative metrics and statistics

No Comments

No Known Activations