INDEX

Explanations

proper nouns related to a specific person or place named "Collins"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Collins."

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

oused

-0.70

ICAN

-0.70

itia

-0.70

ETA

-0.67

istic

-0.66

axter

-0.65

fare

-0.64

 discrep

-0.64

iddled

-0.63

ilitation

-0.63

POSITIVE LOGITS

worth

1.17

creen

0.81

es

0.80

ively

0.78

mount

0.77

uit

0.77

 Collins

0.77

engers

0.76

 Andersen

0.75

boro

0.75

Activations Density 0.057%

proper nouns related to a specific person or place named "Collins"

mentions of the name "Collins."

No Comments

No Known Activations