INDEX

Explanations

phrases indicating a negation or exclusion

oai_token-act-pair · gpt-3.5-turbo

phrases indicating negation or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

lycer

-0.73

igree

-0.66

iership

-0.66

 Presence

-0.62

 Strateg

-0.61

ulative

-0.61

 Rapp

-0.59

 Paint

-0.58

RAFT

-0.58

 Investigators

-0.57

POSITIVE LOGITS

xious

0.96

onday

0.93

xus

0.91

 avail

0.90

oses

0.90

ones

0.85

vell

0.84

obs

0.82

 particular

0.82

ct

0.76

Activations Density 0.038%

phrases indicating a negation or exclusion

phrases indicating negation or denial

No Comments

No Known Activations