INDEX

Explanations

mentions of the word "master" with varying levels of emphasis

oai_token-act-pair · gpt-3.5-turbo

terms related to authoritative positions or roles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OPLE

-0.76

 brim

-0.66

 Bour

-0.66

 allergies

-0.63

odies

-0.63

orescent

-0.62

NPR

-0.62

 Beir

-0.61

omen

-0.60

 membranes

-0.59

POSITIVE LOGITS

master

1.04

mind

1.02

piece

0.89

masters

0.89

å§«

0.87

abilia

0.85

ãĤ¨ãĥ«

0.82

ãĥ¼ãĥĨãĤ£

0.81

hood

0.78

ESS

0.78

Activations Density 0.006%

mentions of the word "master" with varying levels of emphasis

terms related to authoritative positions or roles

No Comments

No Known Activations