INDEX

Explanations

mentions of technology or devices with dual functionalities

oai_token-act-pair · gpt-3.5-turbo

references to dual features or systems

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

FORE

-0.79

otle

-0.76

UFF

-0.73

 Lans

-0.69

 Warehouse

-0.66

uden

-0.65

 Simulator

-0.65

ONEY

-0.64

Interstitial

-0.64

ICAN

-0.64

POSITIVE LOGITS

fold

1.03

ples

0.88

edged

0.85

ities

0.85

ity

0.83

 simultaneous

0.81

 sided

0.77

footed

0.76

otom

0.75

 thirds

0.74

Activations Density 0.015%

mentions of technology or devices with dual functionalities

references to dual features or systems

No Comments

No Known Activations