INDEX

Explanations

phrases related to assessing or questioning the effectiveness of a certain action or program

oai_token-act-pair · gpt-3.5-turbo

terms related to effectiveness and efficacy 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pper

-0.75

hak

-0.71

Rail

-0.71

ODE

-0.70

Pic

-0.68

Earth

-0.68

cise

-0.66

saw

-0.64

nee

-0.64

 Barrel

-0.64

POSITIVE LOGITS

 effectiveness

1.14

iveness

1.11

 destro

0.97

acies

0.91

 confir

0.90

iencies

0.85

 tremend

0.85

 guiActiveUn

0.83

eatures

0.83

olicy

0.82

Activations Density 0.009%

phrases related to assessing or questioning the effectiveness of a certain action or program

terms related to effectiveness and efficacy in various contexts

No Comments

No Known Activations