INDEX

Explanations

phrases related to criminal suspects and police investigations

oai_token-act-pair · gpt-3.5-turbo

references to the term "suspect" in relation to criminal activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unch

-0.76

UNCH

-0.72

galitarian

-0.71

ntil

-0.68

issance

-0.68

andel

-0.67

ummer

-0.66

owan

-0.66

ankind

-0.65

ollen

-0.65

POSITIVE LOGITS

 suspects

0.83

 suspect

0.77

CSI

0.68

 mishand

0.68

istani

0.66

 perpetrator

0.65

itives

0.65

 Snyder

0.65

ively

0.65

 Tsarnaev

0.64

Activations Density 0.022%

phrases related to criminal suspects and police investigations

references to the term "suspect" in relation to criminal activity

No Comments

No Known Activations