INDEX

Explanations

time-related words and numbers

oai_token-act-pair · gpt-3.5-turbo

timestamps and numerical values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

udeb

-0.86

 carbohyd

-0.79

iannopoulos

-0.74

eatures

-0.71

 eleph

-0.71

necess

-0.70

akin

-0.68

 tremend

-0.68

iliated

-0.66

unal

-0.64

POSITIVE LOGITS

 Where

0.94

 Others

0.91

 WRITE

0.90

 Converted

0.89

 Submit

0.87

 =================================================================

0.82

 Miscellaneous

0.82

 Percentage

0.81

 DISTR

0.81

 Classification

0.80

Activations Density 0.086%

time-related words and numbers

timestamps and numerical values

No Comments

No Known Activations