INDEX

Explanations

words related to actions or states of intense scrutiny, targeting, or accumulation

oai_token-act-pair · gpt-3.5-turbo

terms related to attacks or aggressive actions

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

erves

-0.74

Mub

-0.74

zo

-0.73

 Debor

-0.72

ogue

-0.68

ocol

-0.68

nton

-0.67

icular

-0.65

eda

-0.64

 Giul

-0.63

POSITIVE LOGITS

luster

0.90

acked

0.86

intosh

0.84

ACK

0.77

NOW

0.75

DOWN

0.73

acks

0.73

TOP

0.71

lash

0.68

Accessory

0.68

Activations Density 0.016%

words related to actions or states of intense scrutiny, targeting, or accumulation

terms related to attacks or aggressive actions

No Comments

No Known Activations