INDEX

Explanations

terms related to therapy or therapeutic applications

oai_token-act-pair · gpt-3.5-turbo

mentions of therapeutic terms and related concepts

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

ELS

-0.69

urger

-0.65

 lamb

-0.63

 Strauss

-0.63

 rooted

-0.62

 Lomb

-0.62

Elk

-0.61

 Blazers

-0.61

 Blow

-0.61

 Forever

-0.61

POSITIVE LOGITS

apist

1.34

apy

1.21

most

1.06

mop

1.05

nian

1.03

mins

1.01

odynamic

1.00

odynamics

0.98

mal

0.96

anos

0.92

Activations Density 0.048%

terms related to therapy or therapeutic applications

mentions of therapeutic terms and related concepts

No Comments

No Known Activations