INDEX

Explanations

names of specific individuals and companies

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and locations

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

amber

-0.90

graded

-0.82

ngth

-0.80

oire

-0.80

oric

-0.79

pse

-0.79

apy

-0.77

Torrent

-0.76

naire

-0.75

erb

-0.73

POSITIVE LOGITS

 Sanford

1.07

 Gingrich

0.77

 Carlson

0.76

 Ducks

0.76

 Freeze

0.72

 Sail

0.71

 Olson

0.69

 Bernstein

0.69

 Mandela

0.69

emonium

0.68

Activations Density 0.017%

names of specific individuals and companies

proper nouns, particularly names and locations

No Comments

No Known Activations