INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

names and references to individuals, particularly in a statistical or contextual frame

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

pection

-0.79

Î»

-0.68

NetMessage

-0.68

MAR

-0.67

owship

-0.67

nir

-0.67

MET

-0.67

hesda

-0.67

hiba

-0.65

ancial

-0.64

POSITIVE LOGITS

anski

0.80

opa

0.72

haus

0.72

phe

0.67

illions

0.65

jug

0.61

 Balk

0.60

ucl

0.60

atican

0.60

oli

0.58

Activations Density 0.247%

proper nouns

names and references to individuals, particularly in a statistical or contextual frame

No Comments

No Known Activations