INDEX

Explanations

phrases related to written or spoken content

oai_token-act-pair · gpt-3.5-turbo

mentions of future scenarios or depictions in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usercontent

-0.78

.''.

-0.72

.(

-0.71

acci

-0.68

unless

-0.67

 unless

-0.66

 darn

-0.65

cause

-0.65

 instead

-0.64

!.

-0.64

POSITIVE LOGITS

 foregoing

0.63

 Collider

0.57

CES

0.57

Newsletter

0.57

 these

0.57

 this

0.56

Wid

0.56

 Archives

0.56

 Springer

0.56

 hindsight

0.55

Activations Density 0.526%

phrases related to written or spoken content

mentions of future scenarios or depictions in a narrative context

No Comments

No Known Activations