INDEX

Explanations

words related to causing something to happen or creating a certain effect

oai_token-act-pair · gpt-3.5-turbo

instances of the word "induce" and its variations in the context of causing or leading to specific effects or conditions

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

rou

-0.74

fman

-0.73

apest

-0.71

aucus

-0.67

mbuds

-0.66

RAFT

-0.66

 Responsibility

-0.66

Ü

-0.65

Peb

-0.65

andon

-0.64

POSITIVE LOGITS

 induce

0.99

 induced

0.99

 inducing

0.97

induced

0.90

uces

0.90

 induces

0.88

ocy

0.86

 induction

0.86

 abortions

0.84

uced

0.83

Activations Density 0.012%

words related to causing something to happen or creating a certain effect

instances of the word "induce" and its variations in the context of causing or leading to specific effects or conditions

No Comments

No Known Activations