INDEX

Explanations

phrases related to positions or locations within a specific context or structure

oai_token-act-pair · gpt-3.5-turbo

terms associated with the concept of "post" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ADRA

-0.70

 Everywhere

-0.60

DERR

-0.58

cale

-0.58

 PsyNet

-0.56

 Helpful

-0.56

ãħĭ

-0.55

 Disabled

-0.54

vae

-0.54

Ô

-0.52

POSITIVE LOGITS

iest

0.99

ultimate

0.99

liest

0.96

osphere

0.93

ieth

0.81

less

0.80

aments

0.77

able

0.76

lights

0.74

ivist

0.74

Activations Density 0.610%

phrases related to positions or locations within a specific context or structure

terms associated with the concept of "post" in various contexts

No Comments

No Known Activations