INDEX

Explanations

possessive forms with an apostrophe followed by a numerical value indicating strength of activation

oai_token-act-pair · gpt-3.5-turbo

segments of text that contain empty content or delimiters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨ

-0.80

 Seym

-0.77

accompan

-0.70

å§

-0.68

stood

-0.67

 destro

-0.67

 horizont

-0.66

objects

-0.66

 Chero

-0.65

åŃ

-0.64

POSITIVE LOGITS

ead

0.69

rael

0.68

reet

0.68

lash

0.67

 Latest

0.66

hi

0.65

ullivan

0.65

pace

0.64

ourge

0.63

 finest

0.63

Activations Density 0.015%

possessive forms with an apostrophe followed by a numerical value indicating strength of activation

segments of text that contain empty content or delimiters

No Comments

No Known Activations