INDEX

Explanations

text related to the concept of "usage"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "usage" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

sonian

-0.86

inosaur

-0.79

roph

-0.69

ness

-0.67

itude

-0.66

ractive

-0.65

yer

-0.63

ebus

-0.63

uran

-0.63

otics

-0.62

POSITIVE LOGITS

 habits

1.04

 patterns

0.96

 Patterns

0.81

 trends

0.77

CENT

0.75

ername

0.74

ately

0.73

 percentages

0.70

 rates

0.70

Chart

0.69

Activations Density 0.059%

text related to the concept of "usage"

instances of the word "usage" in various contexts

No Comments

No Known Activations