INDEX

Explanations

words related to the effectiveness or efficacy of something

oai_token-act-pair · gpt-3.5-turbo

terms related to efficacy and effectiveness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pper

-0.82

Pic

-0.77

Rail

-0.75

Earth

-0.74

nee

-0.72

ODE

-0.72

space

-0.71

hus

-0.69

hak

-0.67

saw

-0.66

POSITIVE LOGITS

 effectiveness

1.32

 confir

1.11

iveness

1.09

 destro

1.04

 tremend

1.04

 efficacy

0.99

jriwal

0.99

iencies

0.98

 ende

0.97

eatures

0.96

Activations Density 0.010%

words related to the effectiveness or efficacy of something

terms related to efficacy and effectiveness in various contexts

No Comments

No Known Activations