INDEX

Explanations

terms related to encoding and decoding processes

oai_token-act-pair · gpt-3.5-turbo

terms related to coding and encryption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

par

-0.69

 backs

-0.65

 profit

-0.65

cor

-0.61

mob

-0.61

 Tant

-0.60

 prop

-0.60

 summons

-0.59

 claim

-0.59

 towels

-0.59

POSITIVE LOGITS

oding

4.17

oded

2.91

oder

2.15

odes

2.07

ode

2.00

ryption

1.67

osion

1.59

ODE

1.45

rypted

1.44

ategor

1.06

Activations Density 0.011%

terms related to encoding and decoding processes

terms related to coding and encryption

No Comments

No Known Activations