INDEX

Explanations

character sequences that include specific words like "Hydra", "Spy", and "SetKeyMotion"

oai_token-act-pair · gpt-3.5-turbo

specific scientific terms or technical jargon

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

 guid

-0.72

åī

-0.67

å£

-0.64

è¡

-0.62

 ç¥ŀ

-0.61

gins

-0.61

 VIDEOS

-0.61

 rush

-0.60

Kag

-0.60

è£ħ

-0.59

POSITIVE LOGITS

cellence

0.72

lease

0.69

Measure

0.69

Spec

0.67

bnb

0.67

Le

0.66

EStream

0.65

Display

0.63

String

0.62

omatic

0.62

Activations Density 0.149%

character sequences that include specific words like "Hydra", "Spy", and "SetKeyMotion"

specific scientific terms or technical jargon

No Comments

No Known Activations