INDEX

Explanations

names related to a legal or investigative context

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names and terms related to legal cases or events involving notable individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ĨĴ

-0.90

arine

-0.86

uration

-0.80

urations

-0.78

iners

-0.78

esis

-0.76

rise

-0.74

 Gutenberg

-0.73

izations

-0.73

sis

-0.73

POSITIVE LOGITS

senal

0.79

cano

0.76

interstitial

0.73

 Stra

0.71

illo

0.71

butt

0.68

Reply

0.67

geon

0.67

 Henderson

0.65

````

0.64

Activations Density 0.108%

names related to a legal or investigative context

mentions of specific names and terms related to legal cases or events involving notable individuals

No Comments

No Known Activations