INDEX

Explanations

phrases related to arrests or legal actions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating arrests or legal actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Elena

-0.65

 Larson

-0.63

ãĥ´

-0.62

 Ethiop

-0.62

 favors

-0.60

 paran

-0.60

Lub

-0.59

priority

-0.58

 Magicka

-0.58

 mirrors

-0.58

POSITIVE LOGITS

 breakup

0.76

arov

0.71

iry

0.70

 hiatus

0.70

 lockout

0.69

hetamine

0.69

hunt

0.68

 flurry

0.67

 altercation

0.67

 debacle

0.66

Activations Density 0.140%

phrases related to arrests or legal actions

phrases indicating arrests or legal actions

No Comments

No Known Activations