INDEX

Explanations

references to the name "Lucas" combined with numeric values

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Lucas."

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

ãĥĥãĥĪ

-0.73

yer

-0.70

eering

-0.69

req

-0.69

orget

-0.69

lying

-0.69

ifice

-0.67

lain

-0.67

 Seym

-0.66

gencies

-0.66

POSITIVE LOGITS

film

1.30

Film

1.04

 Skywalker

0.90

 Lucas

0.89

eland

0.80

afort

0.79

ious

0.79

itic

0.76

Hunt

0.76

ifer

0.73

Activations Density 0.010%

references to the name "Lucas" combined with numeric values

mentions of the name "Lucas."

No Comments

No Known Activations