INDEX

Explanations

words related to identification documents or processes

oai_token-act-pair · gpt-3.5-turbo

terms related to identification and documentation

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

IFrame

Link

Negative Logits

 Spur

-0.72

pire

-0.71

aft

-0.69

 presided

-0.66

hops

-0.64

fty

-0.62

verse

-0.62

phalt

-0.62

 raining

-0.61

mega

-0.61

POSITIVE LOGITS

 identification

3.83

 Identification

3.04

ID

1.84

IDs

1.79

 ident

1.69

 identity

1.66

 identifying

1.65

 identifier

1.55

 identify

1.49

 identifiers

1.49

Activations Density 0.011%

words related to identification documents or processes

terms related to identification and documentation

No Known Activations