INDEX

Explanations

mentions of the name "Watson"

oai_token-act-pair · gpt-3.5-turbo

references to the name "Watson" 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 @ 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

amera

-0.86

ulatory

-0.76

raft

-0.72

ĩ

-0.70

tera

-0.66

egal

-0.65

ional

-0.65

ual

-0.64

ulation

-0.64

ulated

-0.63

POSITIVE LOGITS

 Holmes

1.03

atson

0.84

 Watson

0.83

bley

0.79

idge

0.77

batch

0.74

ville

0.73

croft

0.72

Whe

0.72

combe

0.71

Activations Density 0.126%

mentions of the name "Watson"

references to the name "Watson" in various contexts

No Comments

No Known Activations