INDEX

Explanations

phrases related to exerting pressure or influence

oai_token-act-pair · gpt-3.5-turbo

instances of pressure being exerted 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 @ 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

sterdam

-0.78

rences

-0.77

idences

-0.76

aces

-0.75

avior

-0.73

onym

-0.73

ilater

-0.72

ances

-0.72

ISA

-0.71

olitics

-0.71

POSITIVE LOGITS

 shoulders

0.92

 pressuring

0.84

 exerted

0.84

 incumbent

0.79

 brakes

0.77

 incumb

0.76

 forcing

0.76

 exert

0.75

 tyres

0.75

 wedge

0.74

Activations Density 0.118%

phrases related to exerting pressure or influence

instances of pressure being exerted in various contexts

No Comments

No Known Activations