INDEX

Explanations

names of individuals who have been arrested or charged with crimes

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names related to individuals and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

parency

-0.72

isphere

-0.72

ashington

-0.69

ipedia

-0.68

ensical

-0.66

fters

-0.65

udos

-0.64

omics

-0.64

ysc

-0.64

igraph

-0.63

POSITIVE LOGITS

1.11

1.06

1.05

1.04

Jr

1.03

1.02

Activations Density 0.210%

names of individuals who have been arrested or charged with crimes

proper nouns and specific names related to individuals and events

No Comments

No Known Activations