INDEX

Explanations

terms related to therapy and medical treatment

oai_token-act-pair · gpt-3.5-turbo

references to various types of therapy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

lihood

-0.71

ership

-0.70

ãĥĥãĥī

-0.67

 Economy

-0.65

abet

-0.65

pol

-0.64

İ

-0.64

umbers

-0.63

ACTED

-0.61

rake

-0.61

POSITIVE LOGITS

 sessions

0.95

 therapy

0.93

otherapy

0.90

apist

0.85

ilitating

0.84

 regimen

0.79

apy

0.78

 therapies

0.78

iatrics

0.75

 treatments

0.73

Activations Density 0.013%

terms related to therapy and medical treatment

references to various types of therapy

No Comments

No Known Activations