INDEX

Explanations

names of people

oai_token-act-pair · gpt-3.5-turbo

words related to actions or processes of speaking or narrating

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

æĥ

-0.64

Wan

-0.64

Lay

-0.63

ISO

-0.62

CHAT

-0.59

 skelet

-0.58

Es

-0.58

Ĥİ

-0.58

prints

-0.57

HM

-0.56

POSITIVE LOGITS

wagen

1.20

ounge

0.95

anguage

0.90

ategory

0.89

ogical

0.87

ength

0.84

ysis

0.84

fleet

0.83

theless

0.81

worth

0.79

Activations Density 0.027%

names of people

words related to actions or processes of speaking or narrating

No Comments

No Known Activations