INDEX

Explanations

verbs related to mental processes such as understanding, seeing, knowing, imagining, and telling

oai_token-act-pair · gpt-3.5-turbo

phrases that express difficulty in understanding or perceiving situations

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

 teasp

-0.79

 earthqu

-0.67

ghan

-0.64

EEK

-0.62

zynski

-0.62

çīĪ

-0.59

PE

-0.59

æĸ¹

-0.58

ippi

-0.58

PLA

-0.58

POSITIVE LOGITS

athom

0.81

detail

0.79

 anymore

0.74

due

0.72

enance

0.71

uate

0.71

notice

0.68

 anything

0.68

 justifies

0.67

successful

0.67

Activations Density 0.121%

verbs related to mental processes such as understanding, seeing, knowing, imagining, and telling

phrases that express difficulty in understanding or perceiving situations

No Comments

No Known Activations