INDEX

Explanations

terms related to the brand "Motorola"

oai_token-act-pair · gpt-3.5-turbo

references to specific smartphone models, particularly from the Motorola brand

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

iday

-0.78

 Kling

-0.76

umbn

-0.75

elaide

-0.72

 Ramsay

-0.71

iting

-0.70

razil

-0.69

lishes

-0.69

nels

-0.69

imental

-0.69

POSITIVE LOGITS

GP

0.97

 Moto

0.91

 Maker

0.83

 Mobility

0.82

 Mods

0.80

itsu

0.77

cycle

0.76

ī

0.72

 contrace

0.72

wake

0.72

Activations Density 0.014%

terms related to the brand "Motorola"

references to specific smartphone models, particularly from the Motorola brand

No Comments

No Known Activations