INDEX

Explanations

words related to causing something to happen or come about

oai_token-act-pair · gpt-3.5-turbo

words and phrases related to the concept of induction or causing specific effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

Ü

-0.73

fman

-0.69

esan

-0.69

RAFT

-0.68

 Pound

-0.67

esides

-0.67

foundation

-0.67

 Thou

-0.66

 Chop

-0.64

aldo

-0.63

POSITIVE LOGITS

 inducing

1.00

 induced

0.98

 induce

0.97

uces

0.96

 induces

0.94

induced

0.92

uced

0.91

orescence

0.90

ocy

0.90

 cele

0.85

Activations Density 0.016%

words related to causing something to happen or come about

words and phrases related to the concept of induction or causing specific effects

No Comments

No Known Activations