INDEX

Explanations

numbers or numerical patterns

oai_token-act-pair · gpt-3.5-turbo

numerical references or identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

loo

-0.89

 Denis

-0.72

WARD

-0.71

RAY

-0.70

RAFT

-0.70

hips

-0.68

REAM

-0.67

iage

-0.66

 Passage

-0.66

bda

-0.66

POSITIVE LOGITS

eral

1.02

emonic

1.01

pty

0.89

phys

0.83

num

0.82

quist

0.80

atsu

0.80

aho

0.75

ocular

0.74

BER

0.74

Activations Density 0.029%

numbers or numerical patterns

numerical references or identifiers

No Comments

No Known Activations