INDEX

Explanations

medical terms and procedures often related to health evaluations and studies

oai_token-act-pair · gpt-3.5-turbo

technical terms and analyses related to health assessments and statistical evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

WIND

-0.73

Planet

-0.73

atron

-0.68

atche

-0.67

ouver

-0.65

Winter

-0.64

Private

-0.64

wire

-0.64

hello

-0.64

Secure

-0.63

POSITIVE LOGITS

 biomark

1.04

 clinically

1.01

ivariate

0.95

 assay

0.94

 analges

0.93

 clinicians

0.93

cyt

0.92

 placebo

0.92

 heterogeneity

0.91

 antidepressant

0.91

Activations Density 0.897%

medical terms and procedures often related to health evaluations and studies

technical terms and analyses related to health assessments and statistical evaluations

No Comments

No Known Activations