INDEX

Explanations

references to the name "Gandolf"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Gandolf."

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

kick

-0.74

alysis

-0.69

Kit

-0.68

 notor

-0.64

organic

-0.62

 porous

-0.59

agra

-0.59

nexus

-0.59

 situ

-0.59

 Achievements

-0.59

POSITIVE LOGITS

dinand

1.35

erick

1.00

stad

0.99

sburg

0.95

sson

0.95

riction

0.88

ocity

0.88

enstein

0.87

olph

0.87

inations

0.87

Activations Density 0.021%

references to the name "Gandolf"

references to the name "Gandolf."

No Comments

No Known Activations