INDEX

Explanations

words related to being on the edge or brink

oai_token-act-pair · gpt-3.5-turbo

gerunds or present participles ending in 'ering'

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

ertodd

-0.68

Kov

-0.67

Running

-0.66

undo

-0.66

 Sterling

-0.63

 freeing

-0.63

fit

-0.63

owler

-0.62

 Kinnikuman

-0.57

 includ

-0.56

POSITIVE LOGITS

igion

0.86

chell

0.74

senal

0.73

loo

0.70

igious

0.70

lust

0.68

beard

0.67

agher

0.67

gger

0.67

luster

0.67

Activations Density 0.032%

words related to being on the edge or brink

gerunds or present participles ending in 'ering'

No Comments

No Known Activations