INDEX

Explanations

specific names, likely associated with a person named Lee

oai_token-act-pair · gpt-3.5-turbo

the name "Lee" in various contexts

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

rontal

-0.78

ALLY

-0.74

ionic

-0.71

ICAN

-0.69

unct

-0.69

ENTION

-0.65

ilateral

-0.62

rious

-0.62

 mistaken

-0.62

security

-0.61

POSITIVE LOGITS

Anne

0.92

utenant

0.84

warm

0.81

vers

0.80

 Stras

0.78

lee

0.78

wei

0.77

 Harvey

0.77

vel

0.77

 Chun

0.77

Activations Density 0.031%

specific names, likely associated with a person named Lee

the name "Lee" in various contexts

No Comments

No Known Activations