INDEX

Explanations

references to writers in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to writers

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

ibaba

-0.81

rals

-0.74

undai

-0.74

eneg

-0.72

illon

-0.71

ypes

-0.70

umph

-0.68

inho

-0.67

ADRA

-0.67

asonic

-0.67

POSITIVE LOGITS

 writer

1.11

 laureate

1.04

writer

0.98

writ

0.90

 writers

0.87

 Writer

0.87

writers

0.85

writing

0.82

 fiction

0.82

uscript

0.81

Activations Density 0.018%

references to writers in various contexts

references to writers

No Comments

No Known Activations