INDEX

Explanations

references to historical time periods, particularly in relation to changes in the atmosphere

oai_token-act-pair · gpt-3.5-turbo

references to historical time periods

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

aspx

-0.91

ĪĴ

-0.76

atin

-0.73

anza

-0.72

mble

-0.69

vez

-0.68

hop

-0.68

ticket

-0.67

eq

-0.66

 lineback

-0.66

POSITIVE LOGITS

opausal

0.86

oded

0.68

osaurs

0.66

ago

0.65

 dawn

0.60

arians

0.60

tale

0.59

 ingrained

0.59

 when

0.59

oland

0.59

Activations Density 0.021%

references to historical time periods, particularly in relation to changes in the atmosphere

references to historical time periods

No Comments

No Known Activations