INDEX

Explanations

controversial or disputed statements or claims

oai_token-act-pair · gpt-3.5-turbo

phrases that introduce significant claims or allegations

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

quer

-0.71

enary

-0.69

æ©

-0.67

bul

-0.64

enum

-0.62

daq

-0.61

ragon

-0.61

AppData

-0.60

iates

-0.60

eng

-0.60

POSITIVE LOGITS

 namely

1.23

 blaming

0.90

 asserting

0.88

 alleging

0.87

 assertion

0.85

 claiming

0.83

 dismissing

0.82

 falsely

0.82

 arguing

0.82

 alienation

0.82

Activations Density 0.330%

controversial or disputed statements or claims

phrases that introduce significant claims or allegations

No Comments

No Known Activations