INDEX

Explanations

references to the word "gorilla" in the text

oai_token-act-pair · gpt-3.5-turbo

the word "gorilla" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ply

-0.93

orough

-0.90

schild

-0.89

den

-0.81

iosyn

-0.80

log

-0.80

matically

-0.77

daq

-0.75

ensible

-0.75

race

-0.75

POSITIVE LOGITS

istas

0.83

 Ammunition

0.83

ieri

0.81

esi

0.81

Ã±o

0.79

 Haram

0.76

 Gomez

0.76

ength

0.75

ista

0.72

emonium

0.70

Activations Density 0.035%

references to the word "gorilla" in the text

the word "gorilla" in various contexts

No Comments

No Known Activations