INDEX

Explanations

Well, this neuron seems to be looking for specific numerical values, especially those related to financial figures

oai_token-act-pair · gpt-3.5-turbo

numerical values and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hol

-0.79

board

-0.75

aways

-0.75

fund

-0.68

cycl

-0.67

agan

-0.66

anol

-0.66

estone

-0.64

away

-0.61

boards

-0.61

POSITIVE LOGITS

1.09

1.07

1.06

1.05

1.04

Activations Density 0.049%

Well, this neuron seems to be looking for specific numerical values, especially those related to financial figures

numerical values and measurements

No Comments

No Known Activations