INDEX

Explanations

references to authority figures or institutions making decisions

oai_token-act-pair · gpt-3.5-turbo

content related to judicial decisions and legal proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Beaut

-0.74

Life

-0.68

Growing

-0.67

 Explosion

-0.65

 Whats

-0.65

 Beauty

-0.63

Dad

-0.62

 Paste

-0.62

Memory

-0.61

 highs

-0.61

POSITIVE LOGITS

 subpoena

1.44

 veto

1.28

 overr

1.22

 unilaterally

1.21

 subpoen

1.20

 filib

1.16

 enforce

1.11

 legisl

1.11

 filibuster

1.10

 acquies

1.09

Activations Density 0.446%

references to authority figures or institutions making decisions

content related to judicial decisions and legal proceedings

No Comments

No Known Activations