INDEX

Explanations

grammatical and medical terms

oai_token-act-pair · gpt-3.5-turbo

words related to grammatical and scientific terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Coinbase

-0.71

IDA

-0.68

 Beans

-0.67

Dek

-0.66

 Username

-0.66

ICH

-0.66

 SERV

-0.66

ITNESS

-0.66

bsite

-0.66

IVERS

-0.65

POSITIVE LOGITS

 impulse

0.82

 tendencies

0.80

looking

0.80

arial

0.79

oric

0.77

ogical

0.71

rontal

0.71

 voices

0.70

 reasoning

0.70

 behaviours

0.70

Activations Density 0.079%

grammatical and medical terms

words related to grammatical and scientific terms

No Comments

No Known Activations