INDEX

Explanations

statements or contexts related to beliefs or convictions

oai_token-act-pair · gpt-3.5-turbo

repeated references to the concept of belief

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

apeake

-0.72

bye

-0.69

ogle

-0.68

agher

-0.68

hire

-0.67

schild

-0.65

cale

-0.65

hma

-0.64

xon

-0.64

yna

-0.63

POSITIVE LOGITS

 belief

0.91

fulness

0.86

ieve

0.84

lessness

0.77

Matrix

0.75

 beliefs

0.75

ieving

0.75

ually

0.74

 faith

0.74

itious

0.73

Activations Density 0.023%

statements or contexts related to beliefs or convictions

repeated references to the concept of belief

No Comments

No Known Activations