INDEX

Explanations

numerical values or codes present in a text

oai_token-act-pair · gpt-3.5-turbo

instances of numerical values or decimal points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 bour

-0.77

 streng

-0.76

 shedding

-0.75

 behavi

-0.71

 breathe

-0.68

ucha

-0.67

 sustaining

-0.67

 affirm

-0.66

 Schne

-0.66

 glim

-0.64

POSITIVE LOGITS

1.12

wordpress

0.96

android

0.96

mil

0.92

services

0.91

com

0.91

amazon

0.89

dk

0.88

common

0.88

yahoo

0.87

Activations Density 0.066%

numerical values or codes present in a text

instances of numerical values or decimal points

No Comments

No Known Activations