INDEX

Explanations

medical or scientific hypotheses

oai_token-act-pair · gpt-3.5-turbo

references to scientific hypotheses and their testing

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

artney

-0.83

thumbnails

-0.78

dos

-0.78

Rated

-0.76

cler

-0.75

luster

-0.71

pine

-0.70

nia

-0.68

zilla

-0.67

ophon

-0.66

POSITIVE LOGITS

icist

0.97

 hypothesis

0.93

 hypothes

0.90

 conjecture

0.87

 hypotheses

0.83

 theories

0.78

 theory

0.73

 posit

0.72

 extrap

0.71

 theor

0.68

Activations Density 0.048%

medical or scientific hypotheses

references to scientific hypotheses and their testing

No Comments

No Known Activations