INDEX

Explanations

references to ratings or evaluations

oai_token-act-pair · gpt-3.5-turbo

ratings that relate to quality or performance, particularly in the context of movies, services, and products

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

ĸļ

-1.02

odcast

-0.80

alam

-0.76

 Canaver

-0.74

utenberg

-0.74

sym

-0.69

ugu

-0.69

 Forth

-0.66

rote

-0.65

hester

-0.65

POSITIVE LOGITS

vation

1.01

rating

0.91

ved

0.90

rated

0.85

 ratings

0.84

 rating

0.83

iation

0.83

ochet

0.78

bucks

0.73

Review

0.73

Activations Density 0.019%

references to ratings or evaluations

ratings that relate to quality or performance, particularly in the context of movies, services, and products

No Comments

No Known Activations