INDEX

Explanations

action-oriented phrases or statements containing the word "always."

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate ongoing actions or continual states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

bia

-0.62

·

-0.61

ettlement

-0.61

ģ«

-0.59

ALLY

-0.59

VICE

-0.58

 presently

-0.58

Yang

-0.58

dm

-0.57

NAME

-0.57

POSITIVE LOGITS

ailable

0.73

ministic

0.70

ounters

0.70

andro

0.67

oin

0.67

 pursu

0.67

rences

0.66

enos

0.65

dule

0.65

theless

0.64

Activations Density 0.181%

action-oriented phrases or statements containing the word "always."

phrases that indicate ongoing actions or continual states

No Comments

No Known Activations