INDEX

Explanations

mentions of the word "ob" with varying degrees of activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ob" in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ivities

-0.77

ÂłÂłÂłÂłÂłÂłÂłÂł

-0.70

 Quan

-0.69

 cort

-0.67

imates

-0.66

ÂłÂłÂłÂł

-0.64

Wr

-0.61

 ORIG

-0.60

++++++++++++++++

-0.59

 Actual

-0.59

POSITIVE LOGITS

acter

1.39

ranch

1.24

server

1.20

edience

1.20

esity

1.19

urden

1.19

acterial

1.18

acteria

1.17

last

1.13

livion

1.10

Activations Density 0.031%

mentions of the word "ob" with varying degrees of activation

occurrences of the word "ob" in varying contexts

No Comments

No Known Activations