INDEX

Explanations

names of historical individuals

oai_token-act-pair · gpt-3.5-turbo

references to historical figures and scholars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ACTION

-0.79

addons

-0.79

 actionGroup

-0.78

inventoryQuantity

-0.76

cffff

-0.75

brainer

-0.75

gary

-0.72

ngth

-0.72

shapeshifter

-0.72

TBD

-0.72

POSITIVE LOGITS

 Lewis

1.01

 Herbert

1.01

 Edward

0.98

 Abraham

0.97

 Francis

0.97

 Alexander

0.96

 Browne

0.96

 Henry

0.94

 Nicol

0.92

Ott

0.92

Activations Density 0.206%

names of historical individuals

references to historical figures and scholars

No Comments

No Known Activations