INDEX

Explanations

adjectives describing the evaluation of something, such as "notable," "important," "great," "fascinating," and "unexpected."

oai_token-act-pair · gpt-3.5-turbo

positive adjectives and descriptors related to various subjects

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

-1.09

abus

-0.93

ully

-0.86

aucus

-0.83

anwhile

-0.82

ordon

-0.81

onto

-0.81

 Originally

-0.80

©¶æ

-0.79

orus

-0.77

POSITIVE LOGITS

 examples

1.16

 aspects

1.06

 moments

1.06

 things

1.04

 ideas

1.03

 developments

1.03

 additions

1.01

 surprises

1.00

 instances

0.99

 occasions

0.98

Activations Density 0.259%

adjectives describing the evaluation of something, such as "notable," "important," "great," "fascinating," and "unexpected."

positive adjectives and descriptors related to various subjects

No Comments

No Known Activations