INDEX

Explanations

elements or components within a system or structure

oai_token-act-pair · gpt-3.5-turbo

terms related to scientific elements or components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

sburgh

-0.80

rontal

-0.80

lishing

-0.77

ceed

-0.75

lisher

-0.74

zee

-0.73

istani

-0.72

cies

-0.70

claimed

-0.68

essed

-0.66

POSITIVE LOGITS

 elements

0.93

als

0.90

ality

0.86

 element

0.84

witz

0.79

ARY

0.76

 abund

0.76

alogy

0.75

aries

0.74

meal

0.74

Activations Density 0.029%

elements or components within a system or structure

terms related to scientific elements or components

No Comments

No Known Activations