INDEX

Explanations

names or abbreviations of organizations or entities

oai_token-act-pair · gpt-3.5-turbo

specific names or terms related to organizations, institutions, or entities

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.93

anwhile

-0.78

 shroud

-0.71

WAYS

-0.70

////////////////////////////////

-0.69

theless

-0.67

ãĤ´ãĥ³

-0.65

terday

-0.64

 silence

-0.64

 writ

-0.63

POSITIVE LOGITS

aci

0.99

atoon

0.91

avia

0.90

urion

0.88

acher

0.86

ivot

0.86

acan

0.85

agen

0.84

ima

0.84

anta

0.83

Activations Density 0.323%

names or abbreviations of organizations or entities

specific names or terms related to organizations, institutions, or entities

No Comments

No Known Activations