INDEX

Explanations

time-related phrases or events in the past or future

oai_token-act-pair · gpt-3.5-turbo

words indicating time and temporal references

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

RTX

-0.76

 Eclipse

-0.68

Wak

-0.67

adena

-0.67

 Deng

-0.62

Ack

-0.62

MC

-0.61

 Aether

-0.60

Sov

-0.60

 Week

-0.60

POSITIVE LOGITS

theless

0.78

£ı

0.77

 opted

0.77

å§«

0.75

 assume

0.74

forth

0.74

 suffice

0.72

 belonged

0.72

 recognise

0.71

 allege

0.71

Activations Density 0.217%

time-related phrases or events in the past or future

words indicating time and temporal references

No Comments

No Known Activations