INDEX

Explanations

adjectives indicating a high degree or level of something

oai_token-act-pair · gpt-3.5-turbo

the word "stronger" 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 @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rolley

-0.85

pty

-0.79

mits

-0.74

 Roche

-0.72

hire

-0.71

adr

-0.70

Hop

-0.68

ffe

-0.68

mberg

-0.67

missions

-0.66

POSITIVE LOGITS

 streng

0.94

 strength

0.94

 than

0.93

 referen

0.91

 veter

0.84

 weaker

0.83

 stronger

0.82

nesses

0.82

 advoc

0.82

intendent

0.82

Activations Density 0.009%

adjectives indicating a high degree or level of something

the word "stronger" in various contexts

No Comments

No Known Activations