INDEX

Explanations

the word "node"

oai_token-act-pair · gpt-3.5-turbo

references to specific nodes and node-related concepts in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.89

eatures

-0.77

giving

-0.77

 Dragonbound

-0.75

ocaust

-0.74

orical

-0.72

taking

-0.71

ospital

-0.65

PLIED

-0.65

esome

-0.64

POSITIVE LOGITS

 nodes

0.93

 node

0.93

js

0.90

JS

0.76

modules

0.69

 Node

0.68

ode

0.68

jing

0.68

odes

0.67

ularity

0.66

Activations Density 0.016%

the word "node"

references to specific nodes and node-related concepts in a technical context

No Comments

No Known Activations