INDEX

Explanations

statements about opinions, beliefs, or evaluations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

statements reflecting people's perceptions or beliefs about themselves and their circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

ornia

-0.84

nesday

-0.77

bernatorial

-0.74

isance

-0.74

hess

-0.73

berus

-0.72

ospons

-0.70

uitous

-0.69

icago

-0.68

alion

-0.67

POSITIVE LOGITS

 conditioned

1.11

 fascinated

1.09

 unaware

1.08

 ignorant

1.04

 accustomed

1.04

 attracted

1.03

 misled

1.03

 unconsciously

1.02

 diseng

1.02

 swayed

1.01

Activations Density 0.291%

statements about opinions, beliefs, or evaluations

statements reflecting people's perceptions or beliefs about themselves and their circumstances

No Comments

No Known Activations