INDEX

Explanations

The main thing this neuron does is find verbs associated with communication, organization, and facilitation

oai_token-act-pair · gpt-3.5-turbo

conditional statements and discussions about necessity or obligation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

opez

-0.77

monds

-0.72

alties

-0.69

ngth

-0.67

dies

-0.67

chev

-0.63

 stripes

-0.62

 selves

-0.62

riors

-0.59

strength

-0.59

POSITIVE LOGITS

 happening

1.16

 happen

0.99

 Happ

0.78

ado

0.77

 occurring

0.76

 unintentional

0.73

 happens

0.70

 SECTION

0.70

 happened

0.69

 achievable

0.69

Activations Density 0.198%

The main thing this neuron does is find verbs associated with communication, organization, and facilitation

conditional statements and discussions about necessity or obligation

No Comments

No Known Activations