INDEX

Explanations

thoughts, beliefs, and opinions indicated by phrases like "in my mind", "no doubt in my mind", and "in our minds"

oai_token-act-pair · gpt-3.5-turbo

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

 unequal

-0.75

ammy

-0.70

 Virt

-0.66

ModLoader

-0.63

 bicycles

-0.63

 pestic

-0.61

 Abuse

-0.61

byn

-0.60

cific

-0.60

Iv

-0.60

POSITIVE LOGITS

cells

0.87

ulsion

0.79

ings

0.76

swer

0.74

gdala

0.73

share

0.72

inations

0.71

sts

0.71

grass

0.70

terday

0.69

Activations Density 0.063%

thoughts, beliefs, and opinions indicated by phrases like "in my mind", "no doubt in my mind", and "in our minds"

No Comments

No Known Activations