INDEX

Explanations

percentages and statistical figures in sentences

oai_token-act-pair · gpt-3.5-turbo

percentages related to statistical data or survey results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

imus

-0.74

uran

-0.72

oria

-0.71

mus

-0.67

 artif

-0.66

 shack

-0.64

aph

-0.64

 tyrann

-0.62

matically

-0.62

itz

-0.60

POSITIVE LOGITS

ecided

0.83

theless

0.79

osuke

0.78

TPS

0.75

okers

0.72

+)

0.71

erest

0.71

 Females

0.70

OGR

0.69

votes

0.69

Activations Density 0.015%

percentages and statistical figures in sentences

percentages related to statistical data or survey results

No Comments

No Known Activations