INDEX

Explanations

dates in specific formats

oai_token-act-pair · gpt-3.5-turbo

instances of missing persons and related police activities

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

 Squadron

-0.64

 cabinets

-0.62

fusc

-0.60

 deduct

-0.60

 Orbit

-0.59

 Intermediate

-0.59

 Spectrum

-0.59

 coins

-0.58

 handles

-0.58

Spect

-0.57

POSITIVE LOGITS

WASHINGTON

1.08

LOS

0.83

HCR

0.83

EVA

0.79

SAN

0.79

celona

0.79

ccording

0.78

ASHINGTON

0.74

hesda

0.73

eport

0.73

Activations Density 0.699%

dates in specific formats

instances of missing persons and related police activities

No Comments

No Known Activations