INDEX

Explanations

words related to specific individuals or names

oai_token-act-pair · gpt-3.5-turbo

words related to specific individuals or characters

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

 nomine

-0.85

ĨĴ

-0.76

 horm

-0.74

 SERV

-0.72

taboola

-0.69

LI

-0.68

ername

-0.68

vernment

-0.67

Offline

-0.66

MAP

-0.65

POSITIVE LOGITS

otide

0.77

pole

0.76

claw

0.71

breaker

0.70

igham

0.69

bery

0.69

ocking

0.67

obl

0.67

cker

0.65

breakers

0.64

Activations Density 0.229%

words related to specific individuals or names

words related to specific individuals or characters

No Comments

No Known Activations