INDEX

Explanations

actions or intentions that are followed by attempts to do something

oai_token-act-pair · gpt-3.5-turbo

actions related to attempts or efforts to do something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

hander

-0.80

workers

-0.77

eyes

-0.76

houses

-0.75

spr

-0.75

era

-0.68

room

-0.68

lined

-0.68

father

-0.67

front

-0.67

POSITIVE LOGITS

 unsuccessfully

1.12

 resusc

0.83

 suicide

0.79

URES

0.78

URE

0.77

llor

0.76

Attempts

0.74

 emulate

0.74

 relocation

0.71

ossibility

0.70

Activations Density 0.041%

actions or intentions that are followed by attempts to do something

actions related to attempts or efforts to do something

No Comments

No Known Activations