INDEX

Explanations

phrases related to exerting force, pressure, or influence

oai_token-act-pair · gpt-3.5-turbo

variations of the word "love" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 lapse

-0.70

STATE

-0.66

UI

-0.63

 Login

-0.62

 mosqu

-0.62

BILITY

-0.61

 flashes

-0.61

 Examination

-0.59

 WARN

-0.58

functional

-0.58

POSITIVE LOGITS

ierrez

0.91

tsky

0.87

ove

0.86

nesday

0.86

ictionary

0.84

 Russo

0.77

anu

0.77

ative

0.74

riction

0.73

letal

0.73

Activations Density 0.015%

phrases related to exerting force, pressure, or influence

variations of the word "love" in different contexts

No Comments

No Known Activations