INDEX

Explanations

phrases related to medical treatments or studies, particularly focusing on placebos

oai_token-act-pair · gpt-3.5-turbo

terms related to placebo effects and controlled experiments

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

lar

-0.72

eur

-0.71

odes

-0.69

Allen

-0.69

Publisher

-0.69

 Universe

-0.68

orian

-0.66

Leod

-0.66

ticket

-0.64

 Mysteries

-0.64

POSITIVE LOGITS

 placebo

0.90

 analges

0.82

psey

0.76

veyard

0.75

 trials

0.75

 halves

0.72

 baseline

0.70

 recharge

0.65

 cessation

0.65

etheless

0.65

Activations Density 0.016%

phrases related to medical treatments or studies, particularly focusing on placebos

terms related to placebo effects and controlled experiments

No Comments

No Known Activations