INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people and places

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 seminal

-0.70

 vacuum

-0.68

 multiplying

-0.64

 constellation

-0.64

 kicker

-0.64

[&

-0.63

 respectively

-0.63

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.63

CPI

-0.62

 Spice

-0.61

POSITIVE LOGITS

romeda

1.09

anyahu

1.07

agascar

1.04

odore

1.03

jamin

1.03

hesda

1.00

vertising

1.00

withstanding

0.99

gomery

0.97

anie

0.97

Activations Density 0.309%

names of individuals or entities

proper nouns, specifically names of people and places

No Comments

No Known Activations