INDEX

Explanations

verbs indicating taking action or making changes

oai_token-act-pair · gpt-3.5-turbo

the word "make" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

-0.73

 scrimmage

-0.63

---------

-0.62

 Vest

-0.61

 Leban

-0.61

 Ging

-0.60

 nurs

-0.59

Mub

-0.58

bour

-0.58

 Wick

-0.58

POSITIVE LOGITS

 sure

1.04

hift

0.94

ailable

0.84

emort

0.82

awaru

0.82

urate

0.78

iversal

0.77

itives

0.76

amera

0.74

itions

0.74

Activations Density 0.130%

verbs indicating taking action or making changes

the word "make" in various contexts

No Comments

No Known Activations