INDEX

Explanations

proper nouns related to the name "Rodriguez"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Rodriguez."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

liest

-1.07

fare

-0.86

liness

-0.85

phis

-0.84

mble

-0.82

olulu

-0.81

ths

-0.76

elong

-0.74

ERAL

-0.74

ãĥĩãĤ£

-0.73

POSITIVE LOGITS

 Rodriguez

0.85

irez

0.77

otti

0.75

icer

0.74

encia

0.73

 Gonzalez

0.70

Rod

0.69

 Gomez

0.68

 Squadron

0.67

cano

0.65

Activations Density 0.017%

proper nouns related to the name "Rodriguez"

references to the name "Rodriguez."

No Comments

No Known Activations