INDEX

Explanations

mentions or references to individuals named "Rod" with varying degrees of specificity

oai_token-act-pair · gpt-3.5-turbo

references to the name "Rod" 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Columb

-0.81

pants

-0.66

 Violet

-0.66

creen

-0.65

 Prairie

-0.64

 Sunny

-0.63

 Kashmir

-0.62

 Isles

-0.62

 Clare

-0.61

 Chiefs

-0.61

POSITIVE LOGITS

erick

1.22

endum

0.99

Rod

0.98

gers

0.96

olf

0.96

olph

0.94

rig

0.94

ynam

0.94

amn

0.92

ricks

0.92

Activations Density 0.010%

mentions or references to individuals named "Rod" with varying degrees of specificity

references to the name "Rod" in various contexts

No Comments

No Known Activations