INDEX

Explanations

references to memory or memoirs, especially with emphasis on personal experiences

oai_token-act-pair · gpt-3.5-turbo

references to memory-related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ASC

-0.73

 Highlander

-0.71

 foremost

-0.71

 Icelandic

-0.69

 Strauss

-0.68

 boiling

-0.67

 Palmer

-0.67

 Nordic

-0.67

RAFT

-0.66

 Ducks

-0.66

POSITIVE LOGITS

oir

1.17

phis

1.12

orable

1.10

mem

1.05

cript

1.04

eor

1.03

bered

1.02

oleon

1.01

orial

1.01

ograp

1.01

Activations Density 0.007%

references to memory or memoirs, especially with emphasis on personal experiences

references to memory-related concepts

No Comments

No Known Activations