INDEX

Explanations

references to militia groups and related activities

oai_token-act-pair · gpt-3.5-turbo

references to various types of militia groups

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

âĸ¬

-0.73

paren

-0.69

mone

-0.69

 Wheat

-0.68

ectar

-0.67

èª

-0.66

eating

-0.66

 Prediction

-0.64

val

-0.64

Oracle

-0.63

POSITIVE LOGITS

 militias

1.12

 militia

1.09

 commanders

0.92

 brig

0.89

 commander

0.86

 members

0.84

 patrols

0.83

ilitary

0.83

 paramilitary

0.80

 councill

0.80

Activations Density 0.016%

references to militia groups and related activities

references to various types of militia groups

No Comments

No Known Activations