INDEX

Explanations

phrases related to a sequence of events

oai_token-act-pair · gpt-3.5-turbo

the phrase "after that" indicating a sequence of events or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Rated

-0.70

 Cosponsors

-0.69

IUM

-0.66

ELY

-0.62

 Meaning

-0.61

 Swanson

-0.61

OB

-0.60

Ry

-0.59

Tan

-0.59

mor

-0.59

POSITIVE LOGITS

 pesky

1.03

 fateful

0.90

 settles

0.72

 initial

0.71

 happens

0.71

icter

0.71

emetery

0.69

 ordeal

0.69

 debacle

0.67

 sucker

0.66

Activations Density 0.079%

phrases related to a sequence of events

the phrase "after that" indicating a sequence of events or actions

No Comments

No Known Activations