INDEX

Explanations

names of people and places

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names and terms related to a particular context or topic

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

edience

-0.95

eering

-0.89

quished

-0.82

arily

-0.81

orney

-0.81

quartered

-0.77

ially

-0.77

uyomi

-0.77

 Dragonbound

-0.76

etitive

-0.76

POSITIVE LOGITS

zo

0.87

Sz

0.77

Vor

0.75

Ò

0.74

wp

0.69

artifacts

0.68

 Wilde

0.67

zos

0.67

stre

0.64

asus

0.62

Activations Density 0.072%

names of people and places

mentions of specific names and terms related to a particular context or topic

No Comments

No Known Activations