INDEX

Explanations

terms related to the concept of replicability or inexplicability

oai_token-act-pair · gpt-3.5-turbo

words related to applicability and relevance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Dare

-0.68

 traps

-0.68

 privilege

-0.67

 vigilance

-0.66

trap

-0.64

EMOTE

-0.63

 rapists

-0.62

 Guards

-0.62

 patriotism

-0.61

 prog

-0.61

POSITIVE LOGITS

icable

3.95

icably

3.74

essel

1.77

[/

1.23

enz

1.11

istar

0.96

 noticeable

0.86

ilde

0.84

icative

0.80

 Flames

0.76

Activations Density 0.028%

terms related to the concept of replicability or inexplicability

words related to applicability and relevance

No Comments

No Known Activations