INDEX

Explanations

specific actions taken by different entities or individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "did" and its context in relation to actions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

astern

-0.71

EPA

-0.70

inational

-0.69

é¾įå

-0.69

istani

-0.67

isl

-0.66

zin

-0.65

clair

-0.65

arest

-0.65

PF

-0.64

POSITIVE LOGITS

its

1.22

Its

1.15

 itself

1.10

ITS

1.10

Its

0.95

 their

0.85

 mascot

0.81

 sponsoring

0.81

 THEIR

0.81

 Their

0.81

Activations Density 0.534%

specific actions taken by different entities or individuals

occurrences of the word "did" and its context in relation to actions

No Comments

No Known Activations