INDEX

Explanations

references to statements made in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "said" 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

Occup

-0.79

atown

-0.70

otin

-0.68

trump

-0.68

ãĥ¼ãĥĨ

-0.67

odox

-0.67

ï¸

-0.64

cffffcc

-0.64

oÄŁan

-0.64

ãĥ¡

-0.63

POSITIVE LOGITS

its

0.77

 goodbye

0.75

 yesterday

0.73

 spokesman

0.70

 spokeswoman

0.68

 inspector

0.64

ITS

0.64

 earlier

0.64

undle

0.63

 troopers

0.61

Activations Density 0.203%

references to statements made in different contexts

instances of the word "said" in various contexts

No Comments

No Known Activations