INDEX

Explanations

references to a specific entity or location named "Ma"

oai_token-act-pair · gpt-3.5-turbo

the occurrences of the term "Ma" or terms closely related to it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

tap

-0.68

AAP

-0.65

ttes

-0.64

lined

-0.64

 unaccompanied

-0.61

side

-0.60

 infectious

-0.60

deck

-0.59

rer

-0.59

 unprotected

-0.58

POSITIVE LOGITS

ureen

1.56

estro

1.46

ples

1.25

arten

1.25

urer

1.11

ude

1.08

ury

1.08

hend

1.08

plin

1.04

isel

1.04

Activations Density 0.016%

references to a specific entity or location named "Ma"

the occurrences of the term "Ma" or terms closely related to it

No Comments

No Known Activations