INDEX

Explanations

words related to definitions and explanations

oai_token-act-pair · gpt-3.5-turbo

terms related to definitions and their variations

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

estern

-0.79

 Pradesh

-0.75

ocamp

-0.73

orld

-0.73

olulu

-0.71

vertisement

-0.70

ieri

-0.69

ili

-0.68

pload

-0.68

eor

-0.68

POSITIVE LOGITS

inition

1.00

witz

0.83

initions

0.82

 definitions

0.82

 definition

0.81

lessly

0.79

 defines

0.76

 Definition

0.71

VID

0.70

ality

0.70

Activations Density 0.023%

words related to definitions and explanations

terms related to definitions and their variations

No Comments

No Known Activations