INDEX

Explanations

references to a specific term or location, "Sh"

oai_token-act-pair · gpt-3.5-turbo

references to the term "Sh."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

etheless

-1.00

anwhile

-0.81

 numbered

-0.78

ãĥ¼ãĥĨãĤ£

-0.76

ãĥ¼ãĥĨ

-0.75

 confir

-0.74

 Ajax

-0.71

IUM

-0.70

OLOGY

-0.68

 Leth

-0.67

POSITIVE LOGITS

allow

1.19

aky

1.14

ooting

1.12

ifty

1.12

attering

1.11

uff

1.11

isha

1.10

attered

1.10

aken

1.10

apesh

1.09

Activations Density 0.021%

references to a specific term or location, "Sh"

references to the term "Sh."

No Comments

No Known Activations