INDEX

Explanations

locations and names with the suffix "-ford"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Ford."

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

Magikarp

-0.92

ntil

-0.85

ngth

-0.77

 psychiat

-0.72

jriwal

-0.69

 federally

-0.69

undown

-0.68

 exha

-0.68

ichick

-0.67

acca

-0.67

POSITIVE LOGITS

shire

1.71

ford

0.95

wall

0.93

hurst

0.92

leigh

0.83

doms

0.82

gate

0.81

ham

0.81

ness

0.80

erer

0.79

Activations Density 0.016%

locations and names with the suffix "-ford"

mentions of the name "Ford."

No Comments

No Known Activations