INDEX

Explanations

timestamps in a specific format

oai_token-act-pair · gpt-3.5-turbo

numerical dates and related time 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

ozo

-0.77

agos

-0.76

orc

-0.72

 suscept

-0.70

matic

-0.67

rimination

-0.67

matically

-0.67

olester

-0.66

negie

-0.65

ortium

-0.64

POSITIVE LOGITS

0.95

0.93

0.92

0.90

0.89

0.88

0.86

0.84

Activations Density 0.015%

timestamps in a specific format

numerical dates and related time references

No Comments

No Known Activations