INDEX

Explanations

governmental or administrative entities

oai_token-act-pair · gpt-3.5-turbo

references to governing or organizational bodies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Kafka

-0.69

 Dickens

-0.69

 Channel

-0.62

 Hoover

-0.61

kers

-0.61

 Dreams

-0.60

 Novel

-0.59

 Griffith

-0.59

 Garrison

-0.59

BILITY

-0.57

POSITIVE LOGITS

guards

0.99

chair

0.87

 politic

0.82

guard

0.81

fat

0.78

chairs

0.78

builder

0.78

member

0.78

weight

0.76

builders

0.76

Activations Density 0.018%

governmental or administrative entities

references to governing or organizational bodies

No Comments

No Known Activations