INDEX

Explanations

words related to places

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "capability" or "potential" in various contexts

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

 Monstrous

-0.78

 Masquerade

-0.70

 phyl

-0.69

 explan

-0.67

âĸ¬âĸ¬

-0.66

 Leia

-0.65

 cigars

-0.64

 defic

-0.64

 Schwarzenegger

-0.63

BuyableInstoreAndOnline

-0.62

POSITIVE LOGITS

olitan

1.33

oleon

1.27

ropri

1.23

onent

1.14

osite

1.10

ocalypse

1.10

rison

1.08

ocalyptic

1.08

artment

1.07

apa

1.04

Activations Density 0.027%

words related to places

references to the concept of "capability" or "potential" in various contexts

No Comments

No Known Activations