INDEX

Explanations

statements indicating doubt or negation

oai_token-act-pair · gpt-3.5-turbo

negations related to various assertions or claims

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

çīĪ

-0.69

insula

-0.67

ãĤ¼ãĤ¦ãĤ¹

-0.65

¿½

-0.64

 Rouge

-0.64

DIT

-0.63

 Maiden

-0.62

sided

-0.62

rpm

-0.62

 Globe

-0.62

POSITIVE LOGITS

 necessarily

1.07

 adequately

1.04

 sufficiently

0.96

really

0.91

icably

0.90

 bother

0.87

icable

0.87

 really

0.86

 bluff

0.86

ional

0.84

Activations Density 0.221%

statements indicating doubt or negation

negations related to various assertions or claims

No Comments

No Known Activations