INDEX

Explanations

words related to important functions or responsibilities

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "role" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Sab

-0.71

£ı

-0.69

False

-0.69

Latest

-0.66

 Rapt

-0.65

agle

-0.64

Hig

-0.63

Ign

-0.62

Pic

-0.61

awk

-0.60

POSITIVE LOGITS

 roles

1.06

 role

0.95

role

0.88

 reversal

0.87

ioned

0.80

 incent

0.80

playing

0.77

 model

0.76

 models

0.73

inic

0.72

Activations Density 0.026%

words related to important functions or responsibilities

references to the concept of "role" in various contexts

No Comments

No Known Activations