INDEX

Explanations

comparative adjectives indicating levels of quality or performance

oai_token-act-pair · gpt-3.5-turbo

comparisons of quality or effectiveness

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

 brothers

-0.66

kefeller

-0.64

 spices

-0.62

arnaev

-0.61

peat

-0.61

 Prin

-0.60

 Punk

-0.59

 Romans

-0.59

 Franks

-0.58

 favourite

-0.58

POSITIVE LOGITS

iary

0.83

 è£ıè

0.77

 BaseType

0.73

onse

0.71

ãĥīãĥ©ãĤ´ãĥ³

0.70

 glance

0.67

åħī

0.66

iaries

0.65

orbit

0.64

ISM

0.64

Activations Density 0.023%

comparative adjectives indicating levels of quality or performance

comparisons of quality or effectiveness

No Comments

No Known Activations