INDEX

Explanations

words related to arguments or points presented in a text

oai_token-act-pair · gpt-3.5-turbo

conjunctions that indicate relationships or connections between various subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

+.

-0.78

jah

-0.76

>.

-0.75

`.

-0.71

$.

-0.70

];

-0.69

added

-0.68

vec

-0.67

Adds

-0.67

].

-0.65

POSITIVE LOGITS

 others

0.86

 other

0.79

rogen

0.78

 subsequent

0.78

rogens

0.77

 consequently

0.76

 associated

0.71

 therefore

0.70

 accompanying

0.66

 consequ

0.65

Activations Density 0.328%

words related to arguments or points presented in a text

conjunctions that indicate relationships or connections between various subjects

No Comments

No Known Activations