INDEX

Explanations

verbs related to physical movement, particularly walking or running

oai_token-act-pair · gpt-3.5-turbo

the repetition of the phrase "around."

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

BT

-0.73

hetical

-0.69

iPhone

-0.69

 Guilty

-0.67

qua

-0.67

ENS

-0.61

 semif

-0.58

 Prol

-0.58

TH

-0.58

anza

-0.58

POSITIVE LOGITS

abouts

0.95

 corners

0.89

clock

0.81

unin

0.79

pread

0.78

atform

0.78

bys

0.75

scan

0.74

essage

0.74

worm

0.73

Activations Density 0.040%

verbs related to physical movement, particularly walking or running

the repetition of the phrase "around."

No Comments

No Known Activations