INDEX

Explanations

phrases indicating surpassing a certain limit or level

oai_token-act-pair · gpt-3.5-turbo

instances of the word "exceed" and its variations 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

olan

-0.75

stown

-0.72

NetMessage

-0.69

Ù

-0.67

raid

-0.66

 Corner

-0.66

hran

-0.65

uay

-0.64

issue

-0.64

si

-0.63

POSITIVE LOGITS

 exceed

0.98

ceed

0.90

 exceeded

0.90

 exceeding

0.81

 expectations

0.75

 exceeds

0.74

ancock

0.73

 surpass

0.72

 amounts

0.69

Activations Density 0.010%

phrases indicating surpassing a certain limit or level

instances of the word "exceed" and its variations in various contexts

No Comments

No Known Activations