INDEX

Explanations

phrases that indicate consecutive occurrences or continuity, emphasizing repetition over time

oai_token-act-pair · gpt-3.5-turbo

phrases indicating sequential occurrences or repetitions

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

ufact

-0.70

 sacrific

-0.69

merce

-0.65

itars

-0.64

 streng

-0.62

arus

-0.61

Marginal

-0.60

irs

-0.58

rament

-0.58

abilia

-0.57

POSITIVE LOGITS

Fla

0.80

dies

0.69

 ..........

0.67

Benz

0.66

agy

0.66

ago

0.65

forth

0.63

 Nieto

0.62

adia

0.62

TPS

0.62

Activations Density 0.015%

phrases that indicate consecutive occurrences or continuity, emphasizing repetition over time

phrases indicating sequential occurrences or repetitions

No Comments

No Known Activations