INDEX

Explanations

phrases related to forceful or coercive actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dragged" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bsite

-0.68

tu

-0.68

 THANK

-0.68

OTOS

-0.67

owler

-0.65

enture

-0.64

ribution

-0.62

irements

-0.62

unicip

-0.62

mac

-0.61

POSITIVE LOGITS

ĸļ

1.02

 drag

0.79

 aggro

0.77

 dragging

0.76

glers

0.71

 dragged

0.69

 baggage

0.68

gers

0.68

alog

0.67

gered

0.66

Activations Density 0.016%

phrases related to forceful or coercive actions

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

No Comments

No Known Activations