INDEX

Explanations

references to technical specifications related to memory and storage capacity

oai_token-act-pair · gpt-3.5-turbo

phrases indicating quantities or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

few

-0.84

cffffcc

-0.82

find

-0.73

render

-0.72

heses

-0.71

 Unsure

-0.70

rh

-0.67

bid

-0.67

imaru

-0.67

æĦ

-0.66

POSITIVE LOGITS

 extra

0.74

 cumulative

0.71

 concentrated

0.71

 additional

0.67

 cargo

0.67

icial

0.66

 interconnected

0.66

 material

0.64

 storage

0.64

 accumulated

0.63

Activations Density 0.079%

references to technical specifications related to memory and storage capacity

phrases indicating quantities or measurements

No Comments

No Known Activations