INDEX

Explanations

phrases related to evaluating the wisdom or merit of an action

oai_token-act-pair · gpt-3.5-turbo

statements regarding the quality of ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

andise

-0.73

wood

-0.72

lighting

-0.71

woods

-0.70

vin

-0.66

ighters

-0.66

anches

-0.65

cious

-0.65

aques

-0.63

ancers

-0.63

POSITIVE LOGITS

ually

0.93

 proposition

0.68

ALLY

0.64

uristic

0.64

 outwe

0.64

 aimed

0.63

 accelerator

0.63

 considering

0.63

Ĥİ

0.62

DEM

0.61

Activations Density 0.026%

phrases related to evaluating the wisdom or merit of an action

statements regarding the quality of ideas

No Comments

No Known Activations