INDEX

Explanations

words related to vehicles or transportation, particularly carriages and the names of individuals associated with them

oai_token-act-pair · gpt-3.5-turbo

nouns related to characters and settings in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

interstitial

-0.82

 jars

-0.80

gur

-0.79

roxy

-0.76

lar

-0.75

sense

-0.74

Kings

-0.73

lator

-0.71

cies

-0.71

jar

-0.70

POSITIVE LOGITS

 Compan

0.90

 Islands

0.75

 Classification

0.73

 Chocobo

0.72

 =================

0.71

 Fant

0.68

 Underground

0.68

 Strikes

0.68

teness

0.67

 Corridor

0.67

Activations Density 0.033%

words related to vehicles or transportation, particularly carriages and the names of individuals associated with them

nouns related to characters and settings in narratives

No Comments

No Known Activations