INDEX

Explanations

names or terms related to individuals or groups

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "amb."

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

kies

-0.73

creen

-0.72

housing

-0.71

naires

-0.71

terday

-0.70

ween

-0.67

knife

-0.64

pport

-0.64

 gaze

-0.64

ãĥīãĥ©ãĤ´ãĥ³

-0.64

POSITIVE LOGITS

ilib

1.03

assador

0.95

assadors

0.94

ulatory

0.85

ilit

0.85

rill

0.85

odies

0.83

ulative

0.81

uilding

0.80

alo

0.80

Activations Density 0.008%

names or terms related to individuals or groups

occurrences of the word "amb."

No Comments

No Known Activations